Relief requirements for public health and humanitarian events are in general both unknown in size and type, and are affected by dynamic and hard to measure factors such as geographic location, local economy, infrastructure, social and political conditions, etc. Preparing for long-term development and response to emergent events often involves uncertainty in timing, scope, or scale. Pre-planning for these situations requires an understanding of forecasting, distribution network design, and strategies for managing the uncertainty. This course will examine methods and models for making pre-planning decisions and explore the significant value that is obtained through informed decision-making in advance of an unpredictable event.
Tactical and strategic members of non-governmental organizations and private corporations involved in the humanitarian relief efforts, U.S. federal government employees, U.S. state or local government employees, humanitarian foundation members, program managers, directors of field operations, disaster relief managers, director of logistics and inventory, and logistics officers
NOTE: Pre-course activities will conducted online using the HELIX online learning management system. Access instructions will be provided to registrants when details become available.
Day 1
Day 2
Provided
Recommended
Students need a laptop with Microsoft Excel and the ability to connect to a high-speed internet connection (internet access is provided for onsite portions of course).
For those interested in earning the Health and Humanitarian Supply Chain Management Certificate, this course is the first of the three-course certificate program. To earn the certificate, participants must register and complete the following courses within three years:
Julie Swann, Ozlem Ergun, Pinar Keskinocak
]]>
Despite having common goals, often the lack of cooperation and coordination between humanitarian organizations results in procurement and allocation inefficiencies. As a result, a systems view of a humanitarian effort is needed to ensure appropriate use of scarce resources to meet the goals at hand. This course will focus on conceptual and modeling skills to understand and effectively manage humanitarian response from a systems perspective. Models will address system characteristics (e.g. demand dependencies) that drive system dynamics and policies to regulate performance. Course topics include methods for improving coordination and collaboration, addressing demand dependencies, and reliably measuring and evaluating system performance.
Tactical and strategic members of non-governmental organizations, private corporations involved in the humanitarian relief efforts, U.S. federal government employees, U.S. state or local government employees, humanitarian foundation members, program managers, directors of field operations, disaster relief managers, director of logistics and inventory, and logistics officers
Upon completion of this course, you will be able to:
NOTE: Pre-course activities will conducted online using the HELIX platform online learning management system. Access instructions will be provided to registrants when details become available.
Coordination and Collaboration – 2 hours
Game Theory/Incentives – 1 hour
System Dynamics - 2 hours
Day 1
Day 2
Day 3
Provided
Recommended
For those interested in earning the Health and Humanitarian Supply Chain Management Certificate, this course is the third and final of the three-course certificate program. To earn the certificate, participants must register and complete the following courses within three years:
Julie Swann, Ozlem Ergun, Pinar Keskinocak
]]>Numerous tactical decisions must be made in the response to a public health or humanitarian event. Many of these decisions are concerned with the timely and efficient procurement, allocation and distribution of resources (e.g. funds, supplies, volunteers) through a supply chain. This course will explore methodologies for tactical decision making, including procurement and inventory policies, strategies for distribution and allocation of limited resources and transportation decisions.
Tactical and strategic members of non-governmental organizations, private corporations involved in the humanitarian relief efforts, U.S. federal government employees, U.S. state or local government employees, humanitarian foundation members, program managers, directors of field operations, disaster relief managers, director of logistics and inventory, and logistics officers
NOTE: Pre-course activities will conducted online using the HELIX platform online learning management system. Access instructions will be provided to registrants when details become available.
Inventory – 2 hours
Resource Allocation – 1 hour
Day 1
Day 2
Day 3
Provided
Recommended
Students need a laptop with Microsoft Excel and the ability to connect to a high-speed internet connection (internet access is provided for onsite portions of course).
For those interested in earning the Health and Humanitarian Supply Chain Management Certificate, this course is the second of the three-course certificate program. To earn the certificate, participants must register and complete the following courses within three years:
Julie Swann, Ozlem Ergun, Pinar Keskinocak
]]>ISyE Hosts Yale University's Edward H. Kaplan for its Distinguished Scholarship Lecture on Monday, March 28, 2016. It will take place in the Molecular Science and Engineering Building Auditorium, Cherry Logan Emerson Lecture Theater from 3 p.m. - 4 p.m. A reception will immediately follow the lecture.
Kaplan is William N. and Marie A. Beach Professor of Operations Research, Professor of Public Health, and Professor of Engineering at Yale University, as well as president of INFORMS.
He will be speaking on "Adventures in Policy Modeling!" Policy modeling refers to the application of operations research, statistics, and other quantitative methods to model policy problems. Recognizing that analyses of all sorts often exhibit diminishing returns in insight to effort, the hope is to capture key features of various policy issues with relatively simple “first-strike” models. Problem selection and formulation thus compete with the mathematics of solution methods in determining successful applications: Where do good problems come from? How can analysts tell if a particular issue is worth pursuing?
In addressing these questions, Dr. Kaplan will review some personal adventures in policy modeling selected from public housing, HIV/AIDS prevention, bioterror preparedness, suicide bombings and counterterrorism, in vitro fertilization, predicting presidential elections, and sports.
]]>The efficient flow of inbound materials through your supply chain can have a significant impact on cost, quality, service, and delivery to your customer. With continued pressures from globalization, market volatility, and innovation expectations, companies are extending their reliance on lean principles to outside the four walls of the manufacturing facility. Lean inbound logistics requires strategic coordination to synchronize suppliers, transportation providers and multiple supply chain partners. And like all complex multi-party operations, the road to improvement will have its challenges. Such hurdles could include balancing inventory cost with transportation cost, the lack of leadership understanding and support, and the realities of incumbent manufacturing and procurement contracts and systems.
This course focuses on the why and how to implement lean logistics to support the lean supply chain operations – both in manufacturing and distribution. Areas of focus include: lean strategy development, identifying and overcoming operational realities, and learning the tools necessary for successful implementation.
Special Note: Includes a tour of the port of Savannah
Company owners, consultants, logistics service providers, chief supply chain officers, vice presidents of sales operations, vice presidents and directors of process improvement, and executive, senior, vice presidents, and directors of supply chain, logistics, procurement, manufacturing, or distribution
This course provides a deeper understanding of the PMBOK knowledge areas of project integration and procurement applied in the supply chain vendor selection and management process. To keep pace with the continuous moves toward outsourcing of operations and the advancement of technology, companies need to focus on selecting the right suppliers and partnerships to provide the most value to their customers and to remain profitable. This course provides the knowledge, skills, and tools to ensure that you are selecting the right supply chain partners (including 3PL’s) based on your business goals. Emphasis is placed on understanding alternative techniques for supplier selection including applied quantitative decision making techniques.
This free 1-hour webinar will focus on the why and how to implement milk run strategies to support the lean supply chain operations - both in manufacturing and distribution, and how the efficient flow of inbound materials through your supply chain can have a significantly positive impact on cost, quality, service, and delivery to your customer. With continued pressures to reduce inventory carrying costs, companies are extending their reliance on lean principles to support end-to-end material flow strategies. Lean inbound logistics requires strategic coordination to synchronize suppliers, transportation providers and multiple supply chain partners. And like all complex multi-party operations, the road to improvement will have its challenges. Such hurdles could include minimizing total logistics costs, identifying the prioritized roadmap and playbook for milk run development and execution, and supplier engagement best practices. The webinar will also provide an overview of topics covered at part of the LIVE course hosted by the Supply Chain and Logistics Institute at Georgia Tech.
Brad Bossence, instructor for the GTSCL Lean Inbound Logistics course and Vice President at LeanCor Supply Chain Group will host the session. He will be joined by Reemer Youmans, Director of Distribution Center Operations & Supply Chain at HUGO BOSS Fashions, Inc. Reemer is a graduate of the Lean Supply Chain Professional Certificate series and will discuss his experience with professional education in lean supply chain.
After attending this webinar, attendees will receive a promo code for a discount towards the "Lean Inbound Logistics" course being taught in Savannah, GA February 17-18, 2016!
Learn more about the GTSCL Certificate Series at http://www.scl.gatech.edu/certificates.
We strongly encourage students to act now to seek internships, capstones, and full-time employment (rather than waiting until the end of the semester). Supply Chain Day is a terrific opportunity to pursue opportunities. Plus, enjoy a free pizza lunch!
Where: ISyE Main Bldg, 2nd Floor Atrium
When: Thursday, January 21, 11:15AM-2:15PM
What: The session will include:
Please plan on staying for the duration of the event and bring copies of your resume and business cards. Dress is business casual.
The event is sponsored through the generosity and support of APICS - Atlanta Chapter. APICS is a non-profit educational organization addressing operations management and supply chain management issues, and providing professional development opportunities to its members. APICS Membership is free for full time students. Join today at www.apics.org/join and start networking at local APIC Atlanta events. Also make sure to stop by the APICS table at the event.
]]>ABSTRACT:
Today's era of cloud computing is powered by massive data centers. A data center network enables exchange of data in the form of packets among the servers within these data centers. Given the size of today's data centers, it is desirable to to design low complexity scheduling algorithms which result in a fixed average packet delay, independent of the size of the data center. We consider the scheduling problem in an input-queued switch, which is a good abstraction for a data center network. In particular, we study the queue length (equivalently, delay) behavior under the so-called MaxWeight scheduling algorithm, which has low computational complexity. Under various traffic patterns, we show that the algorithm achieves optimal scaling of the heavy-traffic scaled queue length with respect to the size of the switch. This settles one version of an open conjecture that has been a central question in the area of stochastic networks. We obtain this result by using a Lyapunov-type drift technique to characterize the heavy-traffic behavior of the expected total queue length in the network, in steady-state.
Bio
Siva Theja Maguluri is a Research Staff Member in the Mathematical Sciences and Analytics Department at IBM T. J. Watson Research Center. He obtained his PhD from University of Illinois at Urbana Champaign, in Electrical and Computer Engineering where he worked on resource allocation algorithms for cloud computing and wireless networks. Earlier, he received an MS in ECE and an MS in Applied Math from UIUC and a B.Tech in Electrical Engineering from IIT Madras. His research interests include Stochastic Processes, Optimization, Cloud Computing, Data Centers, Resource Allocation and Scheduling Algorithms, Wireless Networks, and Game Theory
]]>ABSTRACT:
We consider the problem of how to control the measures of false scientific discoveries in high-dimensional models. Towards this goal, we focus on the uncertainty assessment for low dimensional components in high-dimensional models. Specifically, we propose a novel decorrelated likelihood based framework to obtain valid p-values for generic penalized M-estimators. Unlike most existing inferential methods which are tailored for individual models, our method provides a general framework for high-dimensional inference and is applicable to a wide variety of applications, including generalized linear models, graphical models, classifications and survival analysis. The proposed method provides optimal tests and confidence intervals. The extensions to general estimating equations are discussed. Finally, we show that the p-values can be combined to control the false discovery rate in multiple hypothesis testing.
Bio
Dr. Ning is a post-doctoral fellow in the department of Operations Research and Financial Engineering at the Princeton University. Prior to joining into the Princeton University, he was a visiting scholar in the department of Statistics and Actuarial Science at the University of Waterloo. He received his Ph.D in Biostatistics from the Johns Hopkins University. He has received numerous awards in statistics, including best student paper award from International Biometric Society and David Byar young investigator award from American Statistical Association. His research interests focus on the uncertainty assessment in data analysis with applications to biology, medicine and public health.
]]>ABSTRACT:
For many problems in statistical machine learning and data-driven decision-making, massive datasets necessitate the use of scalable algorithms that deliver sensible (interpretable) and statistically sound solutions. In this talk, we discuss several scalable algorithms that directly promote well-structured solutions in two related contexts: (i) sparse high-dimensional linear regression, and (ii) low-rank matrix completion, both of which are particularly relevant in modern machine learning. In the context of linear regression, we study several boosting algorithms – which directly promote sparse solutions – from the perspective of modern first-order methods in convex optimization. We use this perspective to derive the first-ever computational guarantees for existing boosting methods and to develop new algorithms with associated computational guarantees as well. In the context of matrix completion, we present an extension of the Frank-Wolfe method in convex optimization that is designed to induce near-optimal low-rank solutions for regularized matrix completion problems, and we derive computational guarantees that trade off between low-rank structure and data fidelity. For both problem contexts, we present computational results using datasets from microarray and recommender system applications.
Bio
Paul Grigas is a fifth year Ph.D. student in Operations Research at MIT. His research interests include large-scale convex optimization, statistical machine learning, and data-driven decision making. Paul is also interested in applications in online advertising and data analytics, among other areas. Paul was recently awarded the 2015 INFORMS Optimization Society Student Paper Prize, and he was the recipient of an NSF Graduate Research Fellowship. Before coming to MIT, Paul earned a B.S. in Operations Research and Information Engineering from Cornell University.
]]>
Professionals and students, please join the APICS Atlanta Chapter Tuesday, February 16th 6:30-8:30pm for its next professional dinner meeting (PDM) of the 2016 Program Year. Network with professionals and listen to an inspiring presentation. This is a fantastic opportunity to expand your network, gain insights about the industry, and potentially find your passion.
We are very pleased to be featuring a “Georgia Department of Economic Development Update”, presented by Jannine Miller. Ms. Miller is the Director of the Center of Innovation for Logistics, a division of the Georgia Department of Economic Development and the state's leading resource for fueling logistics industry growth and global competitiveness. The Center provides technical industry expertise, collaborative research and partnerships to help the state's logistics industry connect, compete and grow. The Center also hosts the annual Georgia Logistics Summit, which had over 2,000 attendees in 2014.
Previously, Ms. Miller served as the Senior Manager of Finance for The Home Depot; the Executive Director of the Georgia Regional Transportation Authority (GRTA), Transportation Policy Adviser to Governor Purdue, Policy and Programs Consultant for the Georgia State Road and Tollway Authority, and as Senior Transportation Planner with the Atlanta Regional Commission.
Attendees must register online to attend. GT students are free, non-members $35. See the APICS Atlanta website for more details.
]]>ABSTRACT:
We study joint chance constraints where the distribution of the uncertain parameters is only known to belong to an ambiguity set characterized by the mean and support of the uncertainties and by an upper bound on their dispersion. This setting gives rise to pessimistic (optimistic) ambiguous chance constraints, which require the corresponding classical chance constraints to be satisfied for every (for at least one) distribution in the ambiguity set. We provide tight conditions under which pessimistic and optimistic joint chance constraints are computationally tractable, and we show numerical results that illustrate the power of our tractability results.
Bio
Grani A. Hanasusanto is a postdoctoral researcher at the École Polytechnique Fédérale de Lausanne. He holds a PhD degree in Operations Research from Imperial College London and an MSc degree in Financial Engineering from the National University of Singapore. His research focuses on the design and analysis of tractable solution schemes for decision-making problems under uncertainty, with applications in operations management, energy systems, machine learning and data analytics.
]]>
How do we maximize employee engagement toward C-level goals? How does the work inside of an organization connect to the C-level targets? How can we maximize value at the lowest cost with respect for employees?
Join our webinar for an overview presentation and live Q&A with the lead instructor of our Lean Supply Chain Professional certificate series.
The purpose of the Lean Supply Chain Professional certificate program is to transform the way supply chain professionals think, act and lead. Upon completion of the program, participants will be able to develop, lead and implement strategic and tactical elements of lean principles in the supply chain. We are committed to building individuals into serious, results-based Lean Supply Chain Professionals.
ABOUT THE PRESENTER
Brad Bossence is instructor of the Georgia Tech Lean Essentials for the Supply Chain Professional course and Vice President of Leancor Supply Chain Group.
]]>ABSTRACT:
In the genomic era, group association tests are of great interest. Due to the overwhelming number of individual genomic features, the power of testing for association of a single genomic feature at a time is often very small, as are the effect sizes for most features. Many methods have been proposed to test association of a trait with a group of features within a functional unit as a whole, e.g. all single nucleotide polymorphisms (SNP) in a gene, yet few of these methods account for the fact that generally a substantial proportion of the features are not associated with the trait. In this paper, we propose to model the association for each feature in the group as a mixture of features with no association and features with non-zero associations to explicitly account for the possibility that a fraction of features may not be associated with the trait while other features in the group are. The feature-level associations are first estimated by generalized linear models; the sequence of these estimated associations are then modeled by a hidden Markov chain. To test for global association, we develop a modified likelihood ratio test based on a log-likelihood function that ignores higher order dependency plus a penalty term. We derive the asymptotic distribution of the likelihood ratio test under the null hypothesis. Furthermore, we obtain the posterior probability of association for each feature, which provides evidence of feature-level association and is useful for potential follow up studies. In simulations and data application, we show that our proposed method performs well as compared to existing group association tests especially when there are only few features associated with the outcome.
Bio
Yichen Cheng received a bachelor's degree in Mathematics and Applied Mathematics from Fudan University, China. After that, Cheng earned a PhD in Statistics from Texas A&M University. Currently, Cheng is working as a Post-doc at Fred Hutchinson Cancer Research Center with research interests in computational statistics and biostatistics.
]]>ABSTRACT:
Mathematical optimization problems arise in all areas of science and engineering. The distinction convex/nonconvex has usually played the role of boundary between "easy" and "hard" problems. In the recent years it was shown that several hard nonconvex problems can be very successfully tackled using so-called convex relaxations. Such techniques have been applied in diverse areas such as signal processing, imaging, statistics, control theory, robotics, power flow, etc.
At the heart of convex relaxation methods lies the question of obtaining tractable representations of a convex hull of a set of points. In this talk I will discuss lifted representations of convex sets, in which the "hard" convex set is expressed as the projection of a simpler one living in a higher-dimensional space. I will present a new method to construct improved semidefinite programming lifts for polytopes and will give two applications of our method. First I will show how it provides the first family of polytopes in increasing dimensions with a growing gap between LP and SDP extension complexity. Second I will show how our method can be used to solve a conjecture of Laurent from 2003 on the Lasserre hierarchy for the maximum cut problem.
Bio
Hamza Fawzi is a PhD candidate at MIT in the Electrical Engineering and Computer Science department, Laboratory for Information and Decision Systems. He obtained a Diplome d’Ingenieur from Mines ParisTech, France in 2010 and a M.S. in Electrical Engineering from UCLA in 2011. He is broadly interested in the theory and applications of mathematical optimization, and more generally in the mathematical and computational aspects of problems in information and decision sciences.
]]>ABSTRACT:
We consider the problem of sequential signal detection in a multistream setup assuming that there is a multichannel system where the number and location of signals (if any) is a priori unknown. We suppose that the data in each stream/channel follow a very general non-i.i.d. stochastic model. Under the assumption that the local log-likelihood ratio processes in the channels converge r-completely to positive and finite numbers, we establish the asymptotic optimality property of a generalized sequential likelihood ratio test and a mixture-based sequential likelihood ratio test. Specifically, we show that both tests minimize the first r moments of the stopping time distribution asymptotically as the probabilities of false alarm and missed detection approach zero. The general detection theory is illustrated by several practical examples. Finally, we discuss the feasibility of both sequential tests in terms of computational complexity and compare their non-asymptotic performance in a simulation study. This is joint work with Georgios Fellouris.
]]>ABSTRACT:
The field of Electrical Power Engineering is undergoing rapid change, spurred by increasing demands for efficiency, the availability of new technologies, the drive to incorporate renewables and the need for for increased security. As such, this field presents unparalleled opportunities for Operations Research. To put it more precisely, there are substantial
opportunities both for developing new research problems within the Operations Research domain, and also for creating contributions to the practice of Power Engineering. In this talk we will survey a number of problem areas, survey previous work, and discuss challenges.
Bio:
Daniel Bienstock is Professor of Operations Research and of Applied Mathematics at Columbia University, where he has been since 1989. He received the PhD in Operations Research from MIT. His work focuses on mathematical optimization and on problems related to critical infrastructure, in particular the power grid; he is the author of two books on these topics. He received the Presidential Young Investigator award, was the recipient of an IBM Faculty Research Partnership award, is an INFORMS fellow, was plenary speaker at the 2004 SIAM Optimization Conference and semi-plenary speaker at the 2005 ISMP. He is the Editor-in-Chief of Mathematical Programming Computation.
]]>ABSTRACT:
The reliability of k-out-of-n:G systems has received attention due to its importance as a redundant configuration. The k-out-of-n pairs:G balanced system, which requires balancing the arrangement of units, is an emerging area for investigation due to the increase in its applicability in aerospace and military industries and unmanned aerial systems. In this presentation, we investigate the reliability of k-out-of-n pairs:G balanced systems. We propose a heuristic for reliability estimation for symmetrically balanced and unbalanced systems. The computational effort in estimating the reliability of such systems for large number of pairs is discussed. We provide numerical examples for demonstration. Other topics in reliability engineering will be briefly presented.
Bio:
E. A. Elsayed is Distinguished Professor in the Department of Industrial and Systems Engineering, Rutgers University. He is also the Director of the NSF/ Industry/ University Co-operative Research Center for Quality and Reliability Engineering. His research interests are in the areas of quality and reliability engineering, manufacturing processes and production planning and control. He is a co-author of Quality Engineering in Production Systems, McGraw Hill Book Company. He is also the author of Reliability Engineering, John Wiley and Sons and Analysis and Control of Production Systems, Prentice Hall.
His research has been funded by the DoD, FAA, NSF and industry. Dr. Elsayed has been a consultant for US Army, AT&T Bell Laboratories, Ingersoll-Rand, Johnson & Johnson, Personal Products, AT&T Communications, BellCore and other companies. He served as the Editor-in-Chief of the IIE Transactions and the Editor of the IIE Transactions on Quality and Reliability Engineering. He also served as Editor-in-Chief of Quality Technology and Quality Management. He serves on the editorial boards of eight journals in different capacities.
]]>ABSTRACT:
The Affordable Care Act expands health insurance coverage for Americans, and will increase patient volumes and visits significantly. However, a tremendous amount of provider time is wasted due to the inefficiency of appointment scheduling systems currently in use. Our research proposes and demonstrates that, by factoring patient choice behavior into the design of appointment scheduling systems, providers can significantly improve their service efficiency with only minimal changes to their current practice. Specifically, we develop models that account for heterogeneous patient preferences in appointment choice offering. The provider has a certain number of appointment slots to fill in a day. We consider two possible ways that the provider may interact with patients. First, the provider offers a set of appointment choices to patients, who then choose according to their preferences. This resembles an online appointment scheduling system (e.g., zocdoc.com), which has become increasingly popular among patients and providers. Second, the scheduler may sequentially offer several sets of appointment choices. Imagine in the telephone scheduling context, the scheduler may offer additional choices to patients if the initial offers are not accepted. This may also work for online settings designed in a way that patients do not see all choices in their first attempt of booking appointments. We will discuss the forms and structures of the optimal non-sequential offering and sequential offering policies. We also propose effective heuristics to solve large-scale instances and for practical use. We estimate that, based on medical reimbursement data, the efficiency gains by adopting these policies as opposed to ignoring patient choice behavior can translate into additional revenues of $26-150k per year for a primary care provider that sees 30 patients a day. Theoretically, our work is related to assortment planning in revenue management, bipartite matching in graph theory and admission control in queueing theory. This is joint work with Peter van de Ven (CWI, Netherlands) and Bo Zhang (IBM Watson Research Center).
Bio: Nan Liu is an Assistant Professor of Health Policy and Management at Columbia University’s Mailman School of Public Health. His research focuses on stochastic models, dynamic decision making and applied statistical analysis, with applications to the (health) service industry. Much of his work bridges data analytics and systems modeling, and has focused on the design and control of service systems facing complex customer behaviors. His recent work investigates customer preference and choice in the healthcare market and their impact on healthcare management. In addition, he has done extensive work on health policy research using data-driven operations modeling. His research has been published in leading journals in both fields of operations management and health administration/policy, including Manufacturing & Service Operations Management, Operations Research, Production and Operations Management, Health Services Research, Medical Care Research and Review, and Public Administration Review. His work has received a wide range of media attention including the Washington Post and Crain's New York Business. He received a third prize in the INFORMS Junior Faculty Interest Group (JFIG) Paper Competition and the Calderone Junior Faculty Research Prize awarded by Mailman School of Public Health. Dr. Liu has a B.E. in Civil Engineering from Tsinghua University (Beijing, China) and receives his Ph.D. in Operations Research and M.S. in Statistics from the University of North Carolina at Chapel Hill.
]]>
ABSTRACT:
In this talk I will discuss recent joint work with Mike McCourt (SigOpt, San Francisco) that has led to progress on the numerically stable computation of certain quantities of interest when working with positive definite kernels to solve scattered data interpolation (or kriging) problems.
In particular, I will draw upon insights from both numerical analysis and modeling with Gaussian processes which will allow us to connect quantities such as, e.g., (deterministic) error estimates in terms of the power function with the kriging variance. This provides new kernel parametrization criteria as well as new ways to compute known criteria such as MLE. Some numerical examples will illustrate the effectiveness of this approach.
Bio: Greg Fasshauer is a professor in the Department of Applied Mathematics at the Illinois Institute of Technology in Chicago. He earned his PhD in Mathematics from Vanderbilt University in 1995 and joined IIT in 1997 after spending two years as a visiting assistant professor at Northwestern University. His research focuses on numerical analysis, computation and approximation theory with a special emphasis on kernel-based approximation. Among other things, he has published two monographs on this subject, most recently a joint publication with Mike McCourt entitled “Kernel-based Approximation Methods using MATLAB”.
]]>ABSTRACT:
A number of recent problems of great interest in e-commerce (such as context and location aware recommendations, personalized ’tag' learning, etc.) can be cast as large-scale problems of tensor recovery in three dimensions. Thus motivated, we consider the problem of recovering ‘simple’ tensors from their noisy observations in three dimensions. We provide an efficient algorithm to recover structurally ‘simple' tensors given noisy (or missing) observations of the tensor’s entries; our definition of simplicity subsumes low-rank tensors for a variety of definitions of tensor rank. Our algorithm is practical for large datasets and provides a significant performance improvement over state of the art incumbent approaches to Tensor completion. Further, we establish theoretical recovery guarantees that under certain assumptions are order optimal. Joint work with Andrew Li (MIT ORC).
Bio:
Vivek is interested in the development of new methodologies for large scale dynamic optimization and applications in revenue management, finance, marketing and healthcare. He received his Ph.D. in Electrical Engineering from Stanford University in 2007 and has been at MIT since. Vivek is a recipient of an IEEE Region 6 Undergraduate Student Paper Prize (2002), an INFORMS MSOM Student Paper Prize (2006), an MIT Solomon Buchsbaum Award (2008), an INFORMS JFIG paper prize twice (2009, 2011), the NSF CAREER award (2011), a finalist for the Pierskalla award (2011), MIT Sloan’s Outstanding Teacher award (2013), the INFORMS Simulation Society Best Publication Award (2014), and the INFORMS Pricing and Revenue Management Best Publication Award (2015). Outside of academia, he has contributed to the design of the algorithmic trading strategies of GMO's (a USD 100B + money manager) first high frequency venture and is the co-founder and CTO of a venture-backed predictive analytics startup.
]]>ABSTRACT:
In this talk we consider satisficing models, which, as an approach to decision-making under uncertainty, aims at achieving solutions that satisfy a problem’s constraints as much as possible. Mathematical optimization problems that are related to this form of decision-making include the P-model of Charnes and Cooper (1963), where satisficing is the objective, as well as chance-constrained and robust optimization problems, where satisficing is articulated in the constraints. We first introduce a most general framework of a satisficing model, termed the S-model, which seeks to maximize a satisficing decision criterion in its objective, and the corresponding satisficing-constrained optimization problem that generalizes robust optimization and chance-constrained optimization problems. We then focus on a specific family of a tractable probabilistic S-model, termed the T-model, which, for several different settings of practical interests, leads to efficient and effective ways to mitigate uncertainty. We conclude by illustrating the power of this approach on a class of stochastic maximum coverage problems.
Bio:
Patrick Jaillet is the Dugald C. Jackson Professor in the Department of Electrical Engineering and Computer Science and a member of the Laboratory for Information and Decision Systems at MIT. He is also one of the two Directors of the MIT Operations Research Center. Before MIT, he held faculty positions at the University of Texas at Austin and at the Ecole Nationale des Ponts et Chaussees, Paris. He received a Diplôme d'Ingénieur from France, and a PhD in Operations Research from MIT. His current research interests include on-line and data-driven optimization under uncertainty. He is a Fellow of INFORMS and a member of SIAM.
]]>ABSTRACT:
In many real-world statistical problems, we observe a large number of potentially explanatory variables of which a majority may be irrelevant. For this type of problem, controlling the false discovery rate (FDR) guarantees that most of the discoveries are truly explanatory and thus replicable. In this talk, we propose a new method named SLOPE to control the FDR in sparse high-dimensional linear regression. This computationally efficient procedure works by regularizing the fitted coefficients according to their ranks: the higher the rank, the larger the penalty. This is analogous to the Benjamini-Hochberg procedure, which compares more significant p-values with more stringent thresholds. Whenever the columns of the design matrix are not strongly correlated, we show empirically that SLOPE obtains FDR control at a reasonable level while offering substantial power.
Although SLOPE is developed from a multiple testing viewpoint, we show the surprising result that it achieves optimal squared errors under Gaussian random designs over a wide range of sparsity classes. An appealing feature is that SLOPE does not require any knowledge of the degree of sparsity. This adaptivity to unknown sparsity has to do with the FDR control, which strikes the right balance between bias and variance. The proof of this result presents several elements not found in the high-dimensional statistics literature.
Bio
Weijie Su is a fifth-year Ph.D. student in the Stanford Statistics Department, advised by Emmanuel Candès. In 2011, he received a B.S. in Mathematics and a B.A. in Economics (minor) from Peking University. He spent three summers as an intern at Microsoft Research (Beijing, 2010; Redmond, 2013; and Silicon Valley, 2014).
Weijie is broadly interested in high-dimensional statistics, convex optimization, and applied probability. His main focus is to develop and analyze model selection procedures that address challenges arising from high dimensionality, multicollinearity, and various forms of constraints in modern data analysis.
]]>ABSTRACT:
We develop the first nonparametric learning algorithm for periodic-review perishable inventory systems. In contrast to the classical perishable inventory literature, we assume that the firm does not know the demand distribution a priori but makes the replenishment decision in each period based only on the past sales (censored demand) data. It is well-known that even with complete information about the demand distribution a priori, the optimal policy for this problem does not possess a simple structure. Motivated by the studies in the literature showing that base-stock policies perform near-optimal in these systems, in this paper we focus on finding the best base-stock policy. We first establish an important convexity result, showing that the total holding, lost-sales and outdating cost is convex in the base-stock level. Then, we develop a nonparametric learning algorithm that generates a sequence of order-up-to levels whose running average cost converges to the cost of the optimal base-stock policy. We establish a square-root convergence rate of the proposed algorithm, which is the best possible for this class of problems. The analysis of our algorithm requires a novel method of computing the cycle gradient, and the construction of a bridging problem, which significantly departs from previous studies. We also discuss the strongly convex extension, and conduct numerical experiments to demonstrate the effectiveness of our proposed algorithm. This is a joint work with Huanan Zhang and Xiuli Chao (IOE, UMICH).
Bio:
Cong Shi is an assistant professor in the Department of Industrial and Operations Engineering at the University of Michigan. He is interested in developing algorithmic approaches to inventory and supply chain management, revenue management, and service operations.
]]>ABSTRACT:
We look at models of competition and risk within the context of power system markets. We demonstrate when social optima exist, what properties on risk measures and contracts are needed, and how to solve these problems in large scale practical settings. We look at specific structures that give rise to significant enhancements in computational performance. We position these models within a general setting of Nash Games that include linking equilibrium constraints and situtations where players solve multi-period stochastic programs.
BIO:
Michael C. Ferris is Professor of Computer Sciences and leads the Optimization Group within the Wisconsin Institutes for Discovery at the University of Wisconsin, Madison, USA. He received his PhD from the University of Cambridge, England in 1989.
Dr. Ferris' research is concerned with algorithmic and interface development for large scale problems in mathematical programming, including links to the GAMS and AMPL modeling languages, and general purpose software such as PATH, NLPEC and EMP. He has worked on many applications of both optimization and complementarity, including cancer treatment planning, energy modeling, economic policy, traffic and environmental engineering, video-on-demand data delivery, structural and mechanical engineering.
Ferris is a SIAM fellow, an INFORMS fellow, received the Beale-Orchard-Hays prize from the Mathematical Programming Society and is a past recipient of a NSF Presidential Young Investigator Award, and a Guggenheim Fellowship. He serves on the editorial boards of Mathematical Programming, Transactions of Mathematical Software, and Optimization Methods and Software.
]]>Please join us for the 3rd International Physical Internet Conference (IPIC 2016) taking place June 29-July 1, 2016 on the Georgia Tech campus at Global Learning Center.
IPIC 2016 aims to provide an open forum for researchers, innovators and practitioners to introduce leading edge concepts and methodologies; to review the state-of-the-art technologies and latest projects, and to identify critical issues and challenges for future Physical Internet induced research, innovation and implementation.
Online registration open February 15, 2016, visit www.pi.events to learn more about the conference.
Call for Papers and Contributions
IPIC 2016 invites you to submit an original research or innovation contribution to the conference.
Contributions can take three forms: papers, posters and presentations. Papers and posters will be made widely available on www.pi.events and physicalinternetinitiative.org. Visit www.pi.events/call-for-papers for guidelines, templates, and more information relating to paper submission.
]]>
ABSTRACT:
We propose a class of flexible spectral methods for community detection in directed and undirected networks. These methods extract the clustering information by taking the entry-wise ratios of the
eigenvectors, and can be adapted for different purposes including exploring substructures, incorporating covariates. Some practical guidance about the choice of the number of communities will also be provided. Then we demonstrate using the statistician coauthorship and
citation data collected by ourselves, and show a handful of meaningful communities, such as "high-dimensional data”, "large-scale multiple testing", "Dimensional Reduction”, "Objective Bayes” and “Theoretical Machine Learning", etc.
We strongly encourage students to act now to seek internships, capstones, and full-time employment (rather than waiting until the end of the semester). Supply Chain Day is a terrific opportunity to pursue opportunities. Plus, enjoy a free pizza lunch!
Where: ISyE Main Bldg, 2nd Floor Atrium
When: Tuesday, March 15, 11:15AM-2:15PM
What: The session will include:
Please plan on staying for the duration of the event and bring copies of your resume and business cards. Dress is business casual.
The event is sponsored through the generosity and support of APICS - Atlanta Chapter. APICS is a non-profit educational organization addressing operations management and supply chain management issues, and providing professional development opportunities to its members. APICS Membership is free for full time students. Join today at www.apics.org/join and start networking at local APIC Atlanta events. Also make sure to stop by the APICS table at the event and check out the APICS overview video.
]]>ABSTRACT:
We consider the classical joint pricing and inventory control problem with lost-sales and censored demand in which the customer's response to selling price and the demand distribution are not known a priori, and the only available information for decision-making is the past sales data. Conventional approaches, such as stochastic approximation, online convex optimization, and continuum-armed bandit algorithms, cannot be employed since neither the realized values of the profit function nor its derivatives are known. A major difficulty of this problem lies in the fact that the estimated profit function from observed sales data is multimodal even when the expected pro
fit function is concave. We develop a nonparametric data-driven algorithm that actively integrates exploration and exploitation through carefully designed cycles. The algorithm searches the decision space through a sparse discretization scheme to jointly learn and optimize a multimodal (sampled) profit function, and corrects the estimation biases caused by demand censoring. We show that the algorithm converges to the optimal policy as the planning horizon increases, and obtain the convergence rate of regret.
Bio
Boxiao (Beryl) Chen is a Ph.D. candidate from the department of Industrial and Operations Engineering, University of Michigan, Ann Arbor. Her research focuses on data-driven optimization with applications in supply chain management and revenue management. She is a finalist of the 2015 POMS College of Supply Chain Management Student Paper Competition and receives the Wilson Prize for best student paper from the IOE department.
]]>ABSTRACT:
Due to the limited supply and perishable nature of blood products, effective management of blood collection is critical for high quality healthcare delivery. Whole blood is typically collected over a 6 to 8 hour collection window from volunteer donors at sites, e.g., schools, universities, churches, companies, that are a significant distance from the blood products processing facility and then transported from collection site to processing facility by a blood mobile.
The length of time between collecting whole blood and processing it into cryoprecipitate ("cryo"), a critical blood product for controlling massive hemorrhaging, cannot take longer than 8 hours (the 8 hour collection to completion constraint), while the collection to completion constraint for other blood products is 24 hours. In order to meet the collection to completion constraint for cryo, it is often necessary to have a "mid-drive collection"; i.e., for a vehicle other than the blood mobile to pickup and transport, at extra cost, whole blood units collected during early in the collection window to the processing facility.
In this dissertation, we develop analytical models to: (1) analyze which collection sites should be designated as cryo collection sites to minimize total collection costs while satisfying the collection to completion constraint and meeting the weekly production target (the non-split case), (2) analyze the impact of changing the current process to allow collection windows to be split into two intervals and then determining which intervals should be designated as cryo collection intervals (the split case), (3) insure that the weekly production target is met with high probability.
These problems lead to MDP models with large state and action spaces and constraints to guarantee that the weekly production target is met with high probability. These models are computationally intractable for problems having state and action spaces of realistic cardinality.
We consider two approaches to guarantee that the weekly production target is met with high probability: (1) a penalty function approach and (2) a chance constraint approach. For the MDP with penalty function approach, we first relax a constraint that significantly reduces the cardinality of the state space and provides a lower bound on the optimal expected weekly cost of collecting whole blood for cryo while satisfying the collection to completion constraint. We then present an action elimination procedure that coupled with the constraint relaxation leads to a computationally tractable lower bound. We then develop several heuristics that generate sub-optimal policies and provide an analytical description of the difference between the upper and lower bounds in order to determine the quality of the heuristics.
For the multiple decision epoch MDP model with chance constraint approach, we first note by example that a straightforward application of dynamic programming can lead to a sub-optimal policy. We then restrict the model to a single decision epoch. We then use a computationally tractable rolling horizon procedure for policy determination. We also present a simple greedy heuristic (another rolling horizon decision making procedure) based on ranking the collection intervals by mid-drive pickup cost per unit of expected cryo collected, which results in a competitive sub-optimal solution and leads to the development of a practical decision support tool (DST). Using real data from the American Red Cross (ARC), we estimate that this DST reduces total cost by about 30% for the non-split case and 70% for the split case, compared to the current practice. Initial implementation of the DST at the ARC Southern regional manufacturing and service center supports our estimates and indicates the potential for significant improvement in current practice.
]]>
ABSTRACT:
The efficacy of robust optimization methods has recently been extended to multistage problems with uncertainties bound in predetermined sets. Although current frameworks are general and model a large variety of settings, they cannot accurately describe problems with changing uncertainties. This is instrumental in many applications, because our knowledge about the uncertainties changes throughout the process.
In this talk, we take a step toward generalizing robust optimization approaches to problems with varying uncertainty sets. Extending the pioneering work of Ben-Tal, Goryashko, Guslitzer, and Nemirovski (2004), we provide tractable reformulations for both types of uncertainties, namely for exogenous and endogenous sets. For the first type, we discuss the optimization of radiation therapy plans in the presence of changing hypoxia in clinical cancer cases. For the second type, we discuss a two-stage shortest path application, where the first-stage decisions affect the second-stage uncertainties. This framework encompasses a broad range of real-world applications, in which the first-stage decisions are typically from a countable set, e.g., in machine learning, facility location, knapsack, and routing problems, to name a few.
Bio:
Omid Nohadani is an Associate Professor in the department of Industrial Engineering and Management Sciences at Northwestern University. His primary area of research is robust optimization in convex and nonconvex problems. Nohadani’s applied work addresses a variety of settings: statistics, machine learning, nano-technology, ultrafast optics, cancer therapy, high-performance computing, and vehicle routing. More recently, his interests have focused on the area of healthcare engineering, both from the methodological as well as treatment design aspect. He received his Diploma degree in mathematical physics from the University of Bonn, Germany and a Ph.D. in theoretical physics from the University of Southern California. He was a postdoctoral researcher at the Operations Research Center at MIT and a research fellow and instructor at Harvard Medical School.
]]>ABSTRACT:
Polyhedra are central objects in linear programming, combinatorial optimization and integer programming. I will show recent results based on polyhedral methods that range from binary quadratic programming to algorithmic game theory. The goal is to relate the computational complexity of different problems to the structure of the underlying polyhedra, and to unveil new classes of polynomially solvable instances.
In unconstrained binary programming, the use of polyhedral methods dates back to Padberg, who introduced the boolean quadric polytope. A well-known relaxation of the boolean quadric polytope is the cycle relaxation, on which one can optimize in polynomial time. I will present a characterization of the sign patterns of the objective function that always yield an integral optimal solution over the cycle relaxation.
Next, I will explore Nash equilibrium problems. For congestion games, I will describe a polyhedral reformulation of this equilibrium problem and show that total unimodularity is a key property to find a Nash equilibrium in polynomial time.
I will also discuss results that address more fundamental questions in linear programming. In particular, I will show a new bound on the diameter of lattice polytopes. This bound is tight if the vertices have components in {0,1,2}.
Bio
Carla Michini received a PhD in Optimization in 2012 from University of Rome La Sapienza. In 2011, she was a visiting scholar at CMU Pittsburgh, and from 2012 to 2014 she was a postdoctoral researcher at the Institute for Operations Research at ETH Zürich. Currently, she is a postdoctoral researcher in the Optimization group at the Wisconsin Institute for Discovery of UW-Madison.
Carla’s research focuses on different topics in combinatorial optimization, polyhedral combinatorics and integer programming, and spans both theoretical and algorithmic issues. She is particularly concerned with the study of structural properties of combinatorial problems and with their computational complexity.
]]>
ABSTRACT:
Modern large-scale stochastic systems face much demand and processing variability, and a key challenge is the design of efficient control and scheduling policies that are robust to these uncertainties. In this talk, I will present a novel methodology of designing robust scheduling policies for stochastic networks with applications to emerging sectors such as data centers and intelligent transportation systems. In the first part, I present a robust scheduling policy with performance guarantee, for a new stochastic model of job scheduling in data centers, where jobs are represented as directed acyclic graphs (DAG). I will then visit a long-standing open problem on the stability of the longest-queue-first scheduling policy for open multiclass queueing networks, and resolve this problem for an important special case. In the second part of the talk, I focus on transportation networks. I develop the first exact analysis of fixed-time control for urban networks, and briefly mention a few opportunities and challenges in exploiting feedback control policies. I will conclude the talk with an overview of my research agenda and future research directions.
Bio: Ramtin Pedarsani is a postdoctoral researcher in the Electrical Engineering and Computer Sciences Department at UC Berkeley. He obtained his Ph.D. in Electrical Engineering and Computer Sciences from UC Berkeley in 2015. He received his M.Sc. degree at EPFL in 2011 and his B.Sc. degree at the University of Tehran in 2009. His research interests include stochastic systems, network control, and transportation systems. He is the recipient of the best paper award in the IEEE International Conference on Communications (ICC) in 2014.
]]>One of the most misunderstood elements of Lean thinking is that Lean is primarily about effective supply chain management. Therefore, we need to be able to answer the question "How does Lean apply to the supply chain?" Connecting Lean to supply chain management is the core purpose of Module 2. Students will build upon their knowledge in module one and learn how to apply Lean principles and problem solving to supply chain functions.
The overarching theme for module 2 is "systems thinking," where we understand how "pull and one piece flow" will lead to reductions to "total cost" of the supply chain. Students will once again be challenged to questions mental models such as economies of scale and replace them with mental models such as economies of time. Having completed module 2, students will not only be Lean problem solvers, they will understand how to connect lean and waste reduction to supply chain functions.
Supply chain professionals, logistics professionals, material managers, production control managers, transportation managers, warehousing managers and purchasing managers
ABSTRACT:
Nonconvex optimization naturally arises in many machine learning problems (e.g. sparse learning, matrix factorization, and tensor decomposition). Machine learning researchers exploit various nonconvex formulations to gain modeling flexibility, estimation robustness, adaptivity, and computational scalability. Although classical computational complexity theory has shown that solving nonconvex optimization is generally NP-hard in the worst case, practitioners have proposed numerous heuristic optimization algorithms, which achieve outstanding empirical performance in real-world applications.
To bridge this gap between practice and theory, we propose a new generation of model-based optimization algorithms and theory, which incorporate the statistical thinking into modern optimization. Particularly, when designing practical computational algorithms, we take the underlying statistical models into consideration (e.g. sparsity, low rankness). Our novel algorithms exploit hidden geometric structures behind many nonconvex optimization problems, and can obtain global optima with the desired statistics properties in polynomial time with high probability.
Bio: Tuo Zhao is a PhD student in Department of Computer Science at Johns Hopkins University (http://www.cs.jhu.edu/~tour). His research focuses on high dimensional parametric and semiparametric learning, large-scale optimization, and applications to computational genomics and neuroimaging. He was the core member of the JHU team winning the INDI ADHD 200 global competition on fMRI imaging-based diagnosis classification in 2011. He received Siebel scholarship in 2014 and Baidu’s research fellowship in 2015.
ABSTRACT:
In 2014, the United States spent $3 trillion in health care, equivalent to 17.2% of the US GDP. About one third of this amount ($971.8 billion) is attributed to hospital care. Evidently, even modest efforts for preventing and/or streamlining care in a hospital setting matter.
In this talk, I will outline our recent work leveraging Electronic Health Records at the Boston Medical Center to predict hospitalizations and re-hospitalizations. Our current work makes hospitalization predictions within the next year for heart-disease patients and patients with diabetes, as well as, re-hospitalization predictions within 30 days of general surgery. There are interesting lessons to be learned by working with such data. Specifically, very sparse classifiers that focus on a small feature subset for each patient perform remarkably well. Yet, there are no features that can be eliminated for all patients. In fact, our methods substantially outperform classifiers based on a small set of medically recommended risk factors. It is also true that there are patients with very similar features. This has led us to develop a new joint clustering and sparse classification method which produces strong predictions while discovering hidden patient clusters. Cluster membership of positive predictions can be used to justify them, which is particularly useful to clinicians.
I will also briefly outline work with the Brigham and Women's Hospital on predicting the effect of hard to titrate ICU medications and developing an automated controller, using ideas from adaptive control methods, to optimally infuse such medications.
BIO:
Yannis Paschalidis is a Professor and Distinguished Faculty Fellow of Electrical and Computer Engineering, Systems Engineering, and Biomedical Engineering at Boston University. He is the Director of the Center for Information and Systems Engineering (CISE). He obtained a Diploma (1991) from the National Technical University of Athens, Greece, and an M.S. (1993) and a Ph.D. (1996) from the Massachusetts Institute of Technology (MIT), all in Electrical Engineering and Computer Science. He has been at Boston University since 1996. His current research interests lie in the fields of systems and control, networks, applied probability, optimization, operations research, computational biology, medical informatics, and bioinformatics.
Prof. Paschalidis' work on communication and sensor networks has been recognized with a CAREER award (2000) from the National Science Foundation, the second prize in the 1997 George E. Nicholson paper competition by INFORMS, and the best student paper award at the 9th Intl. Symposium of Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks (WiOpt 2011) won by one of his Ph.D. students for a joint paper. His work on protein docking (with his collaborators) has been recognized for best performance in modeling selected protein-protein complexes against 64 other predictor groups (2009 Protein Interaction Evaluation Meeting). He was an invited participant at the 2002 Frontiers of Engineering Symposium organized by the National Academy of Engineering, and at the 2014 National Academies Keck Futures Initiative (NAFKI) Conference. Prof. Paschalidis is a Fellow of the IEEE and the Editor-in-Chief of the IEEE Transactions on Control of Network Systems.
]]>
ABSTRACT:
Markov decision processes (MDP) is a standard modeling tool for sequential decision making in a dynamic and stochastic environment. When the model parameters are subject to uncertainty, the "optimal strategy" obtained from MDP can significantly under-perform than the model's prediction. To address this, robust MDP has been developed which is based on worst-case analysis. However, several restrictions of the robust MDP model prevent it from practical success, which I will address in this talk. The first restriction of standard robust MDP is that the modeling of uncertainty is not flexible and can lead to conservative solution. In particular, it requires that the uncertainty set is "rectangular" - i.e., it is a Cartesian product of uncertainty sets of each state. To lift this assumption, we propose an uncertainty model which we call “k-rectangular" that generalizes the concept of rectangularity, and we show that this can be solved efficiently via state augmentation. The second restriction is that it does not take into account the learning issue - i.e., how to adapt the model in an efficient way to reduce the uncertainty. To address this, we devise an algorithm inspired by reinforcement learning that, without knowing the true uncertainty model, is able to adapt its level of protection to uncertainty, and in the long run performs as good as the minimax policy as if the true uncertainty model is known. Indeed, the algorithm achieves similar regret bounds as standard MDP where no parameter is adversarial, which shows that with virtually no extra cost we can adapt robust learning to handle uncertainty in MDPs.
Bio: Huan Xu received the B.Eng. degree in automation from Shanghai Jiaotong University, Shanghai, China in 1997, the M.Eng. degree in electrical engineering from the National University of Singapore in 2003, and the Ph.D. degree in electrical engineering from McGill University in 2009. From 2009 to 2010, he was a postdoctoral associate at The University of Texas at Austin. He was an assistant professor at the Department of Mechanical Engineering at the National University of Singapore from 2011 to 2015, and has moved to the Department of Industrial and Systems Engineering as an assistant professor since 2016. His research interests include machine learning, robust optimization, planning and control, and statistics. He has published in premium venues of operations research and of machine learning, including Operations Research, Math Programming, Mathematics of Operations Research, Journal of Machine Learning Research, IEEE Transaction of Information Theory, ICML, NIPS etc. He is an associate editor of IEEE Transactions on Pattern Analysis and Machine Intelligence and is on the editorial board of Computational Management Science.
]]>For 2016, Home Delivery World will be joined by and co-located with Click & Collect USA, ECommerce Show USA, and Retail Technology Show USA March 30-31 at the Atlanta Convention Center at AmericasMart. The events are open to anyone and "Exhibition-only" passes are free. See the respective websites for other options and program details.
A limited number of "All Access" passes will be made available to students in exchange for a day of blogging (grants access to activities in addition to the expo…stop by the SCL suite - Groseclose 228 or email event@scl.gatech.edu for more information).
If you deal or are interested in home delivery, you've been discussing topics like reverse logistics, direct fulfillment, multichannel returns, real-time visibility for inventory, and international expansion.
At the Home Delivery World USA 2016 in Atlanta this March, we give you the perfect opportunity to meet, learn, and network with retailers, grocers, e-tailers, marketplaces, and the leading companies and solution providers in the space.
Learn More | Register to Attend
The Click & Collect Show USA is the first and only event in the US market to gather the heads of delivery operations from the major retailers in the world to discuss how Click & Collect will shape the way consumers collect their goods, either in store or by driving to a collection point.You can choose between visiting the expo and on-floor seminars as a visitor, or registering to attend the full VIP conference.
From in-store pickup to drive thru, lockers, and kiosks approaches, Click & Collect examines the strategies that retailers and carriers are starting to roll out in the US market and that may change the entire home delivery chain.
Learn More | Register to Attend
If you're a professional who deals in the online world, you know that keeping up with innovations in ecommerce is crucial. This is a space where getting left behind is not an option.
At the Ecommerce Show USA 2016 in Atlanta this March, we give you the perfect opportunity to stay ahead of the curve by putting you in the same room with leading etailers like Jet.com, Etsy, Fanatics, and leading ecommerce platforms.
Learn More | Register to Attend
The inaugural Retail Technology Show USA will bring together retailers to discuss the latest retail technology innovation and strategies.
This event will be combined with the ECommerce Show USA, Click & Collect and Home Delivery World to address new models of crowd-sourced delivery, lockers, customer care, retention, personalization, and new customer experience strategies. Retailers looking to learn all they need to know to enhance their delivery and eCommerce programs all in one place choose the right event when signing up for Retail Technology Show USA.
Learn More | Register to Attend
Attend any of the above expos for FREE. With our FREE Visitor Pass, you will have the opportunity to meet, learn, and network anywhere on our expo floor. Leading retailers, etailers, and grocers from across the globe will be there!
If you would like to attend the additional seminars and conference events not included in the expo, please see each respective conference website. Discounts for the full conference are available for groups of 3 or more - for more information please send an email to william.horgan@terrapinn.com or +1 212 379 6320.
]]>Each year, 2,000 logistics professionals attend Georgia's unparalleled logistics event, to learn best practices and connect with colleagues and decision-makers in our industry; making it one of the largest logistics events in the country.
New content for 2016:For more information relating to the event and to register, please visit http://www.georgialogistics.com/logistics-summit/.
]]>ATTEND OUR EDUCATION SEMINARS
SCL faculty will be speaking as part of the MODEX Supply Chain Education Summit Seminars which are free to all attendees.
STUDENT DAYS – April 6 & 7
Student Days will be located in rooms B302-B304. Student Days is a two-day event for academia and industry professionals to engage in real-world discussions about the technologies and the skill sets required for future influencers within the supply chain, material handling and logistics industry.
ABOUT MODEX
There's a reason we call MODEX "the Greatest Supply Chain Show on Earth." It's where 850 of the leading manufacturing and supply chain providers gather to showcase their latest and greatest solutions. If your business needs to maximize operational efficiency and cut costs, your solutions will be waiting at MODEX.
The industry's brightest minds will gather to network and share their perspectives on the ever-evolving state of the supply chain – where it's headed, new ideas, innovation and more. With four powerful keynotes, a supply chain education summit and more than 100 hands-on education sessions, you’re sure to find your edge.
MODEX is FREE to attend. Register today!
]]>ABSTRACT:
Discrete optimization problems naturally appear in science, engineering, and many other areas of technological everyday life. Numerous effective methods for tackling these problems build on the existence of strong convex relaxations, mainly obtained using linear (LP) and semidefinite programming (SDP). Producing these relaxations is by no means trivial, and it is the subject of much classical and recent research.
In this talk, I will show some combinatorial techniques for producing exact LP formulations, and apply them to important problems from the literature. I will also briefly talk about geometric techniques to strengthen non-exact formulations and challenging open problems in the area.
Bio: Yuri Faenza received a M.Sc. in Mathematical Engineering in 2006 from the University "Tor Vergata" of Rome, and a Ph.D. in Operations Research in 2010 from the University "Sapienza" of Rome. He has then been a post-doc in the Mathematics Departments of the University of Padua, EPFL, and University of Brussels.
In 2014 he was awarded an Ambizione fellowship from the Swiss National Science Foundation for his project Tight formulations of 0-1 optimization problems. He decided to pursue his project at EPFL, which he then re-joined in 2015.
His main research interests lie in polyhedral combinatorics, combinatorial optimization, and integer programming.
ABSTRACT:
Events that model risk are typically characterised by rare occurrences. While designing engineering and financial systems, we want to keep the probability of their failure to be low. This necessitates the study of rare events that represent risk in stochastic models commonly used in operations research and financial engineering. In this talk, we first consider one of the classical models in stochastic operations research, namely, many server queues, and discuss how large delays happen in the presence of heavy-tailed jobs. We shall discuss in depth the two types of effects that dominate the tail asymptotics across various loading regimes. While the quantitative distinction between these two manifests itself only in the slowly varying components in a half-loaded two server queue, we shall see that the two effects arise from qualitatively very different phenomena (arrival of one extremely big job (or) two big jobs). This type of classical large deviation analysis accounts for the type of risk fully represented by the model, commonly referred as “known unknowns”. However, there is an alternate type of risk posed by mis-specifying a model, also referred as “model risk” or “unknown unknowns”. In the second part of the talk, we quickly see how new tools, built on the foundations of mass transportation theory, help us address model risk.
Bio: Karthyek Murthy is a post-doctoral research scientist in the Department of Industrial Engineering & Operations Research at Columbia University. He completed his PhD at Tata Institute of Fundamental Research, Mumbai, where his PhD work on rare events was awarded with best PhD dissertation award for the year 2015. His research interests lie broadly in applied probability & stochastic processes, with special emphasis on models that arise in operations research, insurance and mathematical finance. Building on his PhD work on rare events, he has been recently investigating stochastic modeling techniques that are robust to model risk. His works have been recognized with IBM International PhD fellowship and TCS Research fellowships.
]]>ABSTRACT:
The design of any experiment is implicitly Bayesian, with prior knowledge being used informally to aid decisions such as which factors to vary and the choice of plausible causal relationships between the factors and measured responses. Bayesian methods allow uncertainty in these decisions to be incorporated into design selection through prior distributions that encapsulate information available from scientific knowledge or previous experimentation. Further, a design may be explicitly tailored to the aim of the experiment through a decision-theoretic approach with an appropriate loss function.
When designing experiments for nonlinear parametric models, finding a Bayesian optimal design is typically analytically intractable and often computational infeasible. The expected loss usually involves an intractable and high dimensional integral. We will present methodology for mitigating the computational expense of design through combining an application of Gaussian Process (GP) regression models with a cyclic descent (coordinate exchange) optimisation algorithm. We adopt methodology from the field of computer experiments and build a GP emulator for the expected loss. The methods allow optimal designs to be found for previously infeasible problems. We will describe the methodology and demonstrate it on a variety of examples.
Bio: Dave Woods is a Professor of Statistics at the University of Southampton with research interests in the design of experiments and the modelling of the resultant data. He holds a five-year research fellowship from the UK Engineering and Physical Sciences Research Council to develop new Bayesian design of experiments methods for nonparametric and mechanistic models. He gained his PhD from Southampton in 2003, and since then he has developed research programmes in design for nonlinear models, especially for discrete data and generalised linear models, screening experiments, and computer experiments and uncertainty quantification. He works extensively with industry and government, particularly in chemical development with the pharmaceutical industry, and he is an Associate Editor for Technometrics. He was the co-founder of the DEMA series of conferences in design of experiments, the most recent of which was held in Sydney, Australia, in December 2015.
]]>ABSTRACT:
The performance of the CPU core stopped improving around 2005. The Moore's law, however, continues to apply -- not to the single-thread performance -- but the number of cores in each computer. Today, at affordable prices, we can buy 64 CPU-cores workstations, thousand-core GPUs, and even eight-core cellphones. To take advantages of multiple cores, we must parallelize our algorithms -- otherwise, our algorithms won't run any faster on newer computers. For iterative parallel algorithms to have the strong performance, asynchrony is critical. Removing the synchronizations among different cores will eliminate core idling and reduce memory-access congestion. However, some cores now compute with out-of-date information. We study fixed-point iterations of a nonexpansive operator and show that randomized async-parallel iterations will almost surely converge to a fixed point, provided that the operator has a fixed point and the step size is properly chosen. As special cases, novel algorithms for linear equation systems, machine learning, distributed and decentralized optimization are introduced, and numerical performance will be presented for sparse logistic regression and others. This is joint work with Zhimin Peng (UCLA), Yangyang Xu (IMA), and Ming Yan (Michigan State).
Bio: Wotao Yin is a professor in the Department of Mathematics of UCLA. His research interests lie in computational optimization and its applications in image processing, machine learning, and other inverse problems. He received his B.S. in mathematics from Nanjing University in 2001, and then M.S. and Ph.D. in operations research from Columbia University in 2003 and 2006, respectively. Before moving to UCLA, he was with Rice University during 2006-13. He won NSF CAREER award in 2008 and Alfred P. Sloan Research Fellowship in 2009. His recent work has been in optimization algorithms for large-scale and distributed signal processing and machine learning problems.
]]>ABSTRACT:
This thesis investigates how a service provider responsible for completing repairs of durable goods deployed throughout a region can improve profitability by reconfiguring its existing supply chain. This supply chain stocks spare parts inventory both in kits that technicians take to the repair sites and at forward stocking locations (FSLs) distributed throughout the region. The investigation was conducted in three parts.
The first part examines the decision of which spare parts to stock in the kit for a single technician who must complete multiple repairs within a single period. The technician has access at the single FSL to all parts not stocked in the kit but at a time penalty which decreases the likelihood of completing a satisfactory number of repairs by the end of the period. This decision is modeled with a binary optimization problem which has a single probabilistic constraint, namely, that the allocation of spare parts between the kit and the FSL allows the technician to complete the required number of repairs in expectation. Formulated as such, the decision problem is NP-hard. Six heuristics are proposed to quickly find spare parts allocations that have low cost. A method to find a lower bound on the optimal value is developed and then used to demonstrate that many of the heuristics can generate solutions whose costs are within ten percent of optimal. The heuristics are also compared against one another on a test suite of problem instances with important parameters varied over ranges of values. Finally, the first part concludes with a case study in which the heuristics are given real-world data from an industry collaborator.
The second part of the thesis broadens the scope of the first part to include the decision of how to sequence the repairs for the technician given that the geographic locations of the customers are incorporated into the model. The total travel time, which depends on the sequence in which customers are visited, affects the expected number of completed repairs, which again must be above a certain required level in expectation. Travel time, however, does not directly impact the objective to minimize total inventory cost. Given a method for sequencing customers, the decision problem is identical to that in part one. The fact that the customers change from one period to the next is accounted for by evaluating the expected fill rate for a repair kit as an average across multiple customer instances. Heuristics for sequencing customers are proposed and heuristics for determining inventory are reused from the first part of the thesis. It is shown that random routing leads to inventory costs twenty percent higher and almost all benefits of smarter routing are captured by a simple greedy heuristic.
The third and final part of the thesis also broadens the scope of the first part but in a different direction to include the decisions of how many technicians to employ and how many FSLs to maintain. Each technician must complete the repairs assigned to him or her, the number of which depends on the total number of technicians employed, and shares access to inventory at all of the FSLs, the number of which influences the time delay needed to retrieve a part not in the repair kit. The objective of the decision problem is to minimize the average total cost of repair kit inventory, FSL inventory, and technician labor per customer repair job in a single period. A straightforward algorithm to find a good solution, completely specified by a kit-or-FSL decision for all part types, a number of technicians, and a number of FSLs, is motivated by the fact that the inventory-setting algorithms developed in the first part of the thesis can run once given the number of technicians and FSLs. Computational testing shows that a single FSL that stocks all part types and many technicians with empty kits is best and that this configuration can save fifty percent of the total costs for a spare parts supply chain without FSL recourse.
]]>ABSTRACT:
We develop a clustering algorithm which does not requires knowing the number of clusters in advance. Furthermore, our clustering method is rotation-, scale- and translation-invariant. We call it “Affine-invariant Bayesian (AIB) process”. A highly efficient split-merge Gibbs sampling algorithm is proposed. Using the Ewens sampling distribution as prior of the partition and the profile residual likelihoods of the responses under three different covariance matrix structures, we obtain inferences in the form of a posterior distribution on partitions. The proposed split-merge MCMC algorithm successfully and efficiently estimate the partition. Our experimental results indicate that the AIB process outperforms other competing methods. In addition, the proposed algorithm is irreducible and aperiodic, so that the estimate is guaranteed to converge to the true partition.
BIO: Dr. Hsin-Hsiung is an Assistant Professor in the Department of Statistics at University of Central Florida (UCF). Dr. Huang received his Ph.D. in Statistics from the University of Illinois at Chicago and two MS degrees from the Georgia Institute of Technology and National Taiwan University as well as BA and BS from National Taiwan University. His scholarly interests and expertise include Bayesian clustering, classification, genome comparison, robust dimension reduction, and text categorization. His research addresses challenges in analyzing big data in bioinformatics and cybersecurity by developing and evaluating new statistical methods. Examples of his research projects include classifying multiple-segmented viruses, discovering the association of biomarkers and hypertension, as well as business intelligence classification. Dr. Huang has been awarded the 2013 Taiwanese study-abroad student research award when he was a doctoral student at UIC, and the 2016 In-House grant at UCF.
]]>
ABSTRACT:
Longitudinal analysis has three important objectives in biomedical studies: (a) estimating the time-varying population-average and subject-specific covariate effects on the outcome process of interest; (b) predicting the future subject-specific outcome trajectories; (c) evaluating the tracking abilities of important risk factors and health outcomes. Because longitudinal data (which is often referred as functional data) consist repeatedly measured outcome and covariate processes over time, they can be used to accomplish the above three objectives simultaneously. Popular parametric methods for longitudinal analysis, such as the generalized mixed-effects models, are often too restrictive and unrealistic for real applications because of their modeling assumptions. On the other hand, nonparametric models without any structural assumptions could be computationally infeasible and difficult to interpret. We present in this talk some structural nonparametric methods to accomplish the above three objectives, namely estimation, prediction and tracking, based on a class of nonparametric mixed-effects models. Our methods, which use either local kernel-type smoothing or global smoothing via B-splines, have the appropriate model flexibility and computational feasibility, and are useful to answer many scientific questions which could not be properly addressed by parametric or unstructured nonparametric regression models. We demonstrate the application of our methods through a long-term epidemiological study of pediatric cardiovascular risk factors and a series of simulation studies. Asymptotic developments of our methods suggest that the convergence rates of our smoothing estimators depend on the number of subjects as well as the numbers of repeated measurements.
This is the joint work with Xin Tian (OBR/NHLBI)
Bio: Colin O. Wu is senior Mathematical Statistician at the National Heart, Lung and Blood Institute, National Institutes of Health (NHLBI/NIH). He is also Adjunct Professor at Georgetown University School of Medicine and Professorial Lecturer at The George Washington University. Dr. Wu received Ph.D. in statistics from the University of California, Berkeley. His past academic positions include the University of Michigan, the Johns Hopkins University, and Guest Lecturer at University of Maryland, College Park. His professional activities include serving as Guest Editor for Statistics in Medicine, Associate Editor for Biometrics, Data Monitoring Committee member for the United Sates Department of Veterans Affairs, and Sphygmomanometer Committee member for the Association for the Advancement of Medical Instrumentation (AAMI). He is Elected Member of the International Statistical Institute, and Fellow of the American Statistical Association. He has published over 130 peer reviewed articles in statistics, biostatistics and medical journals.
]]>ABSTRACT:
Upon arrival to a ticket queue, a customer is offered a slip of paper with a number on it (indicating the order of arrival to the system) and is told the number of the customer currently in service. The arriving customer then chooses whether to take the slip or balk, a decision based on the perceived queue length and associated waiting time. Even after taking a ticket, a customer may abandon the queue, an event that will be unobservable until the abandoning customer would have begun service. In contrast, a standard queue has a physical waiting area so that abandonment is apparent immediately when it takes place and balking is based on the actual queue length at the time of arrival. We prove heavy traffic limit theorems for the generalized ticket and standard queueing processes in the single server setting, discovering that the processes converge together to the same limit, a regulated Ornstein-Uhlenbeck (ROU) process. One conclusion is that for a highly utilized service sys tem with a relatively patient customer population, the ticket and standard queue performances are asymptotically indistinguishable on the scale typically uncovered under heavy traffic approaches. Next, we heuristically estimate several performance metrics of the ticket queue, some of which are of a sensitivity typically undetectable under diffusion scaling. The estimates are tested using simulation and are shown to be quite accurate under a general collection of parameter settings.
Bio: Jamol Pender is an assistant professor at Cornell ORIE, having completed his Ph.D. at Princeton ORFE and a postdoc at Columbia IEOR.
]]>ABSTRACT:
Cancer is a disease driven by rounds of Darwinian selection on somatic genetic mutations, and recent advances in sequencing technologies is offering new opportunities as well as revealing new challenges in this field. In this talk, I will describe two statistical problems in the genetic analysis of tumors. In the first part, I will describe the problem of allele-specific copy number estimation. Copy number change is a basic type of DNA alteration in tumors, and understanding how they affect the tumor’s genome at the allelic level is fundamental to understanding the tumor’s genetic signature. I will describe a bivariate binomial mixture process for this problem, and a method for detecting change-points in this process. In the second part, I will describe the problem of inferring a tumor’s clonal evolutionary history through repeated bulk DNA sampling. This is similar to classic phylogenetic inference problems, with the key difference being that the observed data are slices of a mixed population. I will describe a framework that we developed to estimate the underlying evolutionary tree by joint modeling single nucleotide mutation and allele-specific copy number profiles.
BIO:
Nancy R. Zhang obtained her doctoral degree in Statistics at Stanford University in 2005. After a year’s post-doctoral study at UC Berkeley, she returned to Stanford as assistant professor in the department of Statistics. She was promoted to associate professor at Stanford in 2011, when she moved to the department of Statistics in the Wharton School at University of Pennsylvania. Currently, she is working in the area of applying statistical concepts to modeling and inference problems in computational genomics. In particular, she is developing computational techniques to study heterogeneous tissues through bulk and single-cell sequencing data.
]]>In this dialogue led by Pearl Alexander and Cheryl Cofield, participants will explore the bullying, incivility, and "lack of collegiality" that falls short of legal or policy violations but, nevertheless, have a dramatically negative impact in workplace and classroom environments. Participants will be introduced to five (5) bully prototypes and contemplate how we might reduce bullying and incivility in the workplace. It is open to all faculty, staff and students.
Space is limited. To register, please RSVP at the link below.
https://events.isye.gatech.edu/workplace-classroom-dialogue
]]>If you're interested in getting more involved with IIE and would like to help run this event, please e-mail iiegeorgiatech@gmail.com with the subject "Spring Picnic 2016 Assistance."
]]>The Garage @ Square on Fifth
848 Spring Street NW
Atlanta, GA 30308
The Georgia Tech Institute for People and Technology (IPaT) and the Georgia Tech Center for Health and Humanitarian Systems (CHHS) are pleased to host the 2016 Disaster Response and Mitigation Forum on April 27, 2016.
Through our keynote and two panel sessions, we are bringing together governmental experts, policy makers, researchers, and decision makers from the public and private sector to share current efforts, research, and new problems identified in the space of disaster and humanitarian response.
The goal for the Forum relates to understanding ways in which to advance science and technology to improve disaster response. The Forum will feature two panels including federal, state and local agency representatives, as well as speakers from NGOs, industry, and academic researchers.
Topics we will explore include:
Through this limited engagement, stakeholders will share, learn, and build problem solving coalitions against the many new and rapidly emerging population-level problems affecting our country and the world at-large.
We are pleased to announce Director Jim Butterworth, Director of the Georgia Emergency Management Agency/Homeland Security, as our keynote. Please click on the Speakers linkto learn more about the speakers who will be with us that day to share their insights and experiences.
Those who are interested in submitting posters, please go to: http://ipat.gatech.edu/disaster-response-and-mitigation-forum-poster-session
Registration cost is free, however registration is required for participation. Please click on the Registration Tab and sign up to join us! We will follow up with a networking reception featuring a poster session at the end of our day.
]]>
ABSTRACT:
For the comparison of two diagnostic markers at a flexible specificity, people apply the difference of two correlated receiver operating characteristic (ROC) curves to identify the diagnostic test with stronger discriminant ability. In this paper, we employ jackknife empirical likelihood (JEL) method to construct confidence intervals for the difference of two correlated continuous-scale ROC curves. Using the jackknife pseudo-sample, we can avoid estimating several nuisance variables which have to be estimated in existing methods. We prove that the smoothed jackknife empirical log likelihood ratio is asymptotically chi-squared distribution. Furthermore, the simulation studies in terms of coverage probability and average length of confidence intervals show the good performance in small samples with a moderate computational cost. A real data set is used to illustrated our method.
This is joint work with Dr. Hanfang Yang
]]>ABSTRACT:
In the information age, many real-world applications such as biosurveillance, manufacturing systems, physical and computer experiments often involve data that are massive, high-dimension or have complicated structures. In some cases it is cheap to collect large-scale data, while in other cases it may be costly or time-consuming to collect them. In either case, it is often non-trivial to extract information from these types of data to make useful decisions.
This dissertation makes methodology contributions to three important subfields of statistics: (i) Large-scale multi-stream quickest change detection, (ii) multichannel profile monitoring and (iii) global optimization of expensive functions. A common feature of the thesis work is the use of shrinkage to the respective subfields to address the challenges of high-dimensional or complicated data. However, since different subfields and applications have different features and challenges, details of the shrinkage techniques vary with the subfield.
This dissertation consists of three chapters. In Chapter 1, we study the problem of online monitoring large-scale data streams, which has many important applications from biosurveillance and quality control to finance and security in modern information age. While many classical quickest change detection methods can be extended from one-dimensional to any K-dimensional, their performances are rather poor when monitoring large K of data streams. This motives us to investigate the effects of dimensionality on the performance of quickest change detection methods. We found out through theoretical analysis that the classical quickest change detection methods often over-emphasize the first-order term of the detection delays and overlook the second-order terms of the detection delays, where the latter often increases linearly as a function of the dimension K. When K is large (e.g., hundreds), the second-order term of the detection delay will likely be comparable to the first-order term, which implies that the nice first-order asymptotic optimality properties have little practical meaning for large K. We propose a novel approach to lessen the dimensionality effects by introducing some shrinkage estimators of the unknown post-change parameters. In addition, we also illustrate the challenge of Monte Carlo simulation of the average run length to false alarm in the context of online monitoring large-scale data streams.
In Chapter 2, we consider the problem of monitoring multichannel profiles that has important applications in manufacturing systems improvement. A concrete motivating example of this work is from a forging process, in which multichannel load profiles measure exerted forces in each column of the forging machine. While various methods have been developed for univariate profile monitoring, they often cannot easily be extended to multichannel profiles. There are two main challenges when monitoring multichannel profiles. The first one is that profiles are high-dimensional functional data with intrinsic inner- and inter-channel correlations, and the second, probably more fundamental, challenge is that the functional structure of multi-channel profiles might change over time, and thus the dimension reduction method should be capable of taking into account the potential unknown change. We develop a novel thresholded multivariate principal component analysis (PCA) method for multi-channel profile monitoring. Our proposed method consists of two steps of dimension reduction: It first applies the functional PCA to extract a reasonable large number of features under the in-control state, and then uses the shrinkage techniques to functional PCAs to further select significant features capturing profile information in the out-of-control state. The choice of tuning parameter for soft-thresholding is provided based on asymptotic analysis, and extensive simulation studies are conducted to illustrate the efficacy of our proposed methodology.
In Chapter 3, we study the problem of global optimization of expensive functions. In modern physical and computer experiments, one often deals with expensive functions in the sense that it may take days or months to evaluate their values at a single input setting. An important problem is how to choose an appropriate setting of the input variables so as to optimize the output. To tackle this question, our proposed method involves two main components: one is the construction of a surrogate model to approximate the true function with much cheaper computation, and the other is the determination of a new input setting for function evaluation based on the surrogate model. After iteratively updating these two components, we optimize the latest surrogate model, which yields the approximation to the optima of the original expensive function. To be specific, we propose an adaptive Radial Basis Function (RBF) based global optimization framework via uncertainty quantification. For the surrogate model, we construct an adaptive RBF-based normal mixture Bayesian surrogate model, where the parameters in the RBFs can be adaptively updated each time a new point is explored. It is crucial to employ the normal mixture Bayesian structure which leads to a more stable surrogate model and avoid over-fitting. Its use can be regarded as a ridge-type regression estimate of model coefficients. For the selection of input setting, we propose a novel criterion to assess the input setting based on the surrogate model, and we choose the inputs that maximize the criterion. Our criterion incorporates the expected improvement (EI) of the function prediction to effectively identify promising areas for the global optima, and its uncertainties to efficiently explore the unknown regions. We conduct numerical studies with standard test functions to understand and compare the empirical performance of our proposed method with a prominent existing method.
]]>ABSTRACT:
This thesis consists of three parts, each of which contributes to an independent topic in the broad area of multi-period supply chain optimization, and provides modeling and solution approaches for the problem in concern.
Part I studies a strategic health workforce planning problem. Analysts predict impending shortages in the health care workforce, and wages for health care workers already account for over 50% of U.S. health expenditures. It is thus increasingly important to adequately plan to meet health workforce demand at reasonable cost. Using infinite linear programming (LP) methodology, we propose an infinite-horizon model for health workforce planning in a large health system for a single worker class, e.g. nurses. We give a series of common-sense conditions any system of this kind should satisfy, and use them to prove the optimality of a natural lookahead policy. We then use real-world data to examine how such policies perform in more complex systems; in particular, our experiments show that a natural extension of the lookahead policy performs well when incorporating stochastic demand growth.
Part II investigates an integrated inventory routing (IRP) and freight consolidation problem for perishable goods with a fixed lifetime. The problem is motivated by the status-quo of logistics in many U.S. markets, but also adapts to relevant two-echelon supply chain optimization problems e.g. combined production planning and distribution. We formulate the problem as a large-scale mixed-integer programming (MIP) model. We propose an iterative solution framework with a decomposition procedure and a local search scheme. In the decomposition, a freight consolidation subproblem is first solved to obtain crucial shipping decisions, and after fixing these a restrictive model generates the other decisions for the integrated problem. The local search aims at fast identification of good neighborhoods by solving an assignment-style MIP which matches the consolidation decision with an IRP subproblem, and gradually strengthens the incumbent solution pool when executed in an iterative fashion. Experiments with empirical demand distributions based on real data demonstrate that 1) the integration can achieve remarkable efficiency compared to a sequential approach of the subproblems; 2) both the decomposition and the local search are effective in solving moderately-sized problem instances that are already challenging in practice.
Part III examines a two-echelon distribution problem which can be viewed as a one-warehouse multi-retailer (OWMR) problem reversed in time flows. Unlike the majority of the OWMR literature, where ordering is uncapacitated and the ordering cost is fixed in each period, we assume more realistic volume-dependent cost structures which can be interpreted as multiple transportation modes with batch capacities. The resulting transportation costs are piecewise linear non-convex functions of the shipping volume. Since this breaks classical optimality properties like zero-inventory-ordering, and the LP relaxation of the natural MIP formulation can be very weak, a straightforward application of previous OWMR methods may not be effective. We first introduce a technique that converts our problem to existing OWMR models by bounding the cost functions, and derive the corresponding worst-case approximation guarantees under each type of the transportation costs. We then treat or approximate the transportation costs as concave batch costs, and propose a polynomial-time 2-approximation algorithm by recombining single-echelon lot sizing subproblem solutions for the special case of full truckload costs, where trucks have an identical capacity and each incurs a fixed cost. This improves the best-known result (i.e. a 3.6-approximation) for the same cost structure. Finally, we utilize subproblem structural properties to prove the asymptotic optimality of a decentralized approach for pertinent two-echelon problems in a wider range of settings.
Considering the independence of each part, we will focus on the last topic at the defense.
]]>Join us to learn:
Register Today! Visit pe.gatech.edu/logistics-sav
]]>From rail, ship, storage, and truck, our professors will make innovative freight logistics ideas relatable to our industry in Southeast Georgia. Hear how trends in freight logistics optimization affect our supply chains.
]]>Many high-valued engineering assets used in the manufacturing and service sectors are today being monitored by hundreds and perhaps thousands of sensors. Typically, the goal is to monitor system performance and degradation for numerous purposes, one of which is the prevention of unexpected failures. This talk focuses on how to effectively utilize sensor data to predict future system degradation and remaining lifetime (aka prognostics). The talk will begin by introducing a basic prognostic framework and how it has been implemented. Next, the talk will also focus on the use Big (Sensor) Data in managing system performance. This will be followed by an open discussion about some of the recently developed state-of-the-art modeling techniques that are being used to help predict and prevent system failures.
Dr. Gebraeel is the Chandler Family associate professor of Industrial and Systems Engineering at Georgia Institute of Technology. He received his MS and PhD in Industrial Engineering from Purdue University, 1998 and 2003, respectively. Dr. Gebraeel’s research interests are in leveraging condition-based sensor data streams to improve the predictability of unexpected failures of engineering systems, and improving subsequent operational and logistical decision making processes. He is a member of the Institute of Operations Research and Management Science (INFORMS), the Institute of Industrial Engineers (IIE), and the American Institute of Aeronautics and Astronautics (AIAA).
For more information contact Lew Roberts at l.roberts@gatech.edu.
]]>
This second annual event will focus onTechnology and Transportation. After opening remarks from Georgia Economic Development Commissioner Chris Carr and Center of Innovation Director Jannine Miller, the keynote panel will explore the critically important and rapidly evolving use of technology by transportation and logistics providers.
This year the event moved locations to expand 60% in capacity, but has also filled with over 300 attendees. The livestream feed provides an opportunity to experience the event from any computer or mobile device. In order to access the livestream feed, viewers should log on to www.georgia.org/logisticslunch on the day of the event.
Opening remarks will be given by Georgia Department of Economic Development Commissioner Chris Carr and Center of Innovation for Logistics Director Jannine Miller. HunterMaclean attorney Chris “Smitty” Smith will serve as moderator of the keynote panel, which will focus on Technology and Transportation.
Topics of discussion will include the various state-of-the-art technologies that are currently being implemented at the Georgia Ports Authority, impending technology such as truck platooning and dynamic sequencing, and the ever-changing use of technology needed to increase productivity and streamline communications within the logistics industry.
]]>We strongly encourage students to act now to seek internships, capstones, and full-time employment (rather than waiting until the end of the semester). Supply Chain Day is a terrific opportunity to pursue opportunities. Plus, enjoy a free pizza lunch!
Where: ISyE Main Bldg, 2nd Floor Atrium
When: Wednesday, September 7, 11:15AM-2:15PM
What: The session will include:
Please plan on staying for the duration of the event and bring copies of your resume and business cards. Dress is business casual.
EVENT SPONSOR
The event is sponsored through the generosity and support of APICS - Atlanta Chapter. APICS is a non-profit educational organization addressing operations management and supply chain management issues, and providing professional development opportunities to its members. APICS Membership is free for full time students. Join today at www.apics.org/join and start networking at local APIC Atlanta events. Also make sure to stop by the APICS table at the event.
]]>Attendance is free, and no registration is required.
Topics:
ISyE Associate Professor
]]>Please join us for the opening ceremony and series of events that follow to learn more and celebrate this new partnership!
Monday, August 22, 2016 | 12pm - 1pm
Clough Commons, 2nd Floor Atrium
Monday, August 22, 2016 | 6pm - 8pm
5 Seasons Brewing Sky Room (#204) | 1000 Marietta Street
Tuesday, August 23, 2016 | 12pm - 2pm
ISyE Main Building Atrium
]]>
(Joint with Guanglin Xu)
Abstract:
We study two-stage adjustable robust linear programming in which the right-hand sides are uncertain and belong to a convex, compact uncertainty set. This problem is NP-hard, and the affine policy is a popular, tractable approximation. We prove that under standard and simple conditions, the two-stage problem can be reformulated as a copositive optimization problem, which in turn leads to a class of tractable, semidefinite-based approximations that are at least as strong as the affine policy. We investigate several examples from the literature demonstrating that our tractable approximations significantly improve the affine policy. In particular, our approach solves exactly in polynomial time a class of instances of increasing size for which the affine policy admits an arbitrarily large gap.
Bio:
Sam Burer is George Daly Professor and Graduate Business Analytics Director in the Department of Management Sciences at the University of Iowa. He received his Ph.D. from the Georgia Institute of Technology, and his professional interests include analytics, operations research, management sciences, and optimization. His research has been supported by grants from the National Science Foundation, and he serves on the editorial boards of Management Sciences, Operations Research, SIAM Journal on Optimization, and Mathematics of Operations Research. He has also served as a Member of the Board of Directors of the INFORMS Computing Society and as a Council Member of the Mathematical Optimization Society.
]]>ABSTRACT:
The talk will focus on two seemingly unrelated topics: (i) existence of prediction strategies that have a performance guarantee for all sequences and (ii) probabilistic inequalities for martingales. We will point to a certain equivalence between these two topics, with the most basic example going back to the work of T. Cover in 1965. In light of the equivalence, we will develop computationally efficient prediction methods for problems with a combinatorial benchmark, even when estimating the correct model is NP-hard. Exploiting the equivalence in the other direction, we show that tail bounds for a certain ratio-type inequality follow with ease from mirror descent with an adaptive step size.
Joint work with K. Sridharan
Bio: Alexander (Sasha) Rakhlin is an Associate Professor of Statistics at the University of Pennsylvania, The Wharton School. He received his Bachelors from Cornell University, a Ph.D. from MIT, and joined Penn after working as a postdoctoral researcher at UC Berkeley. Sasha’s interests span a range of topics, including statistics, machine learning, online prediction, and optimization.
ABSTRACT:
The US is currently experiencing an epidemic of drug abuse caused by prescription opioids and illegal opioid use, including heroin. In addition to crime and social problems, rising levels of drug abuse have led to a sharp increase in overdose deaths in the US as well as significant outbreaks of infectious diseases such as HIV and hepatitis C. How should we deploy limited public health resources to help solve this problem? This talk describes models used to support decision making regarding controlling drug abuse – and associated diseases such as HIV and hepatitis C – in the US. We describe models to evaluate the effectiveness and cost-effectiveness of HIV and drug abuse prevention programs targeted to injection drug users; health impacts of diversion programs for low-level drug offenders; and health impacts of current and potential future opioid prescribing practices in the US. We conclude with a discussion of promising directions for further research.
Bio: Margaret L. Brandeau is Coleman F. Fung Professor of Engineering and Professor of Medicine (by Courtesy) at Stanford University. Her research focuses on the development of applied mathematical and economic models to support health policy decisions. Her recent work has examined HIV and drug abuse prevention and treatment programs, programs to control the spread of hepatitis B virus, and preparedness plans for bioterror response. She is a Fellow of INFORMS and a member of the Omega Rho Honor Society for Operations Research and Management Science. From INFORMS, she has received the Philip McCord Morse Lectureship Award, the President’s Award, the Pierskalla Prize, and the Award for the Advancement of Women in Operations Research and the Management Sciences. She has also received the Award for Excellence in Application of Pharmacoeconomics and Health Outcomes Research from the International Society for Pharmacoeconomics and Outcomes Research (ISPOR) and a Presidential Young Investigator Award from the National Science Foundation, among other awards. Professor Brandeau earned a BS in Mathematics and an MS in Operations Research from MIT, and a Ph.D. in Engineering-Economic Systems from Stanford.
]]>ABSTRACT:
Shared vehicle systems, such as those for bike-sharing (e.g., Citi Bike in NYC, Velib in Paris), car-sharing (e.g., car2go, Zipcar) and ride-sharing (Uber, Lyft, etc.) are fast becoming essential components of the urban transit infrastructure. The technology behind these platforms enable fine-grained monitoring and control tools, including good demand forecasts, accurate vehicle-availability information, and the ability to do dynamic pricing and vehicle repositioning. However, owing to their on-demand nature and the presence of network externalities (wherein setting prices at one place affects the supply at all other locations), optimizing the operations of such systems is challenging. To this end, I will describe how such systems can be modeled using queueing-network models, and talk about two recent projects in which we have developed the theoretical tools for analyzing such systems.
First, I will present a unifying framework for data-driven pricing and optimization in shared vehicle systems. Our approach provides efficient algorithms with rigorous approximation guarantees under a variety of controls (pricing, empty-vehicle repositioning, demand redirection) and for a wide class of objective functions (including welfare and revenue, and also multi-objective problems such as Ramsey pricing). Next, using the particular example of dynamic pricing in ride-sharing platforms, I will discuss how market mechanisms can help us to go beyond data-driven optimization; in particular, I will show how dynamic pricing is not any better than static pricing in general, but rather, how it allows the platform to realize optimal performance with limited knowledge of system parameters.
Based on joint work with Ramesh Johari and Carlos Riquelme at Stanford, Daniel Freund and Thodoris Lykouris at Cornell, and the data science team at Lyft.
]]>High quality contract development and management tools are essential activities in achieving improved levels of performance for all Procurement and Supply Management practitioners. Providing robust contracts and process oversight for your organization is critical for success in the Procurement and Supply Management profession.
Experienced professionals involved in supplier bidding, supplier selection, and contract preparation activities usually have a good understanding of key contractual terms applicable and the appropriate contract type needed for the job. Therefore, this program is designed to increase the contracting preparation and execution competencies of practitioners focusing on contractual terms, types, and structure.
All in all, Best Practices in Contract Development and Management will better prepare practitioners for driving cost savings and mitigating supplier risk through contracting activity. This course is perfect for practitioners responsible for acquisition of materials, labor, equipment and/or professional services.
Category management and strategic sourcing professionals, business unit manager, procurement and purchasing professionals and supply chain management professionals
Participants who successfully complete this course will:
Participants receive a course notebook (i.e. slides, notes, exercises).
No prerequisites. This course can be used as an elective towards our Supply Chain Management (SCM) certificate.
Standard: $950.00, Alumni/Org Discount: $855.00, Certificate: $807.50 (cost of each course when signing up for and paying for a multi-course certificate program).
First time attendees pay the listed course fee. If you are a returning student of the Supply Chain & Logistics Institute (SCL) courses, you will receive a 10% discount which you will enter at the "Check Out" page. Use Coupon Code SCL-Alum.
There are also discounts available for multiple-team member registrations, to those who prepay for all the courses in a specific certificate, to active/retired military, or to members of certain organizations (click this link for a listing).
Discounts cannot be combined. To receive the coupon code for these discounts, call 404-385-8663 or send us an email prior to registration
The program fee for LIVE courses (non-online) includes continental breakfasts, lunches, breaks, parking, internet access, and all classroom materials.
If the Supply Chain & Logistics Institute must cancel a program, registrants will receive a full refund. Georgia Tech, however, cannot assume the responsibility for other costs incurred. Due to program enrollment limits, early registration is encouraged. Registrations will be acknowledged by a letter of confirmation from Professional Education.
Please check in at least 30 minutes before the class start time.
Every effort is made to present the course as advertised herein; however, circumstances may make it necessary to alter the schedule and/or presenters.
ABSTRACT:
The scan statistic is by far the most popular method for anomaly detection, being popular in syndromic surveillance, signal and image processing, and target detection based on sensor networks, among other applications. The use of the scan statistics in such settings yields a hypothesis testing procedure, where the null hypothesis corresponds to the absence of anomalous behavior. If the null distribution is known, then calibration of a scan-based test is relatively easy, as it can be done by Monte Carlo simulation. When the null distribution is unknown, it is less straightforward.
We investigate two procedures. The first one is a calibration by permutation and the other is a rank-based scan test, which is distribution-free and less sensitive to outliers. Furthermore, the rank scan test requires only a one-time calibration for a given data size making it computationally much more appealing. In both cases, we quantify the performance loss with respect to an oracle scan test that knows the null distribution. We show that using one of these calibration procedures results in only a very small loss of power in the context of a natural exponential family. This includes the classical normal location model, popular in signal processing, and the Poisson model, popular in syndromic surveillance. We perform numerical experiments on simulated data further supporting our theory and also on a real dataset from genomics.
Joint work with Rui M. Castro(1), Ervin Tánczos(1), and Meng Wang(2)
(1) Technische Universiteit Eindhoven
(2) Stanford University
The paper is available online at
http://arxiv.org/abs/1508.03002
]]>Abstract
Optimization under uncertainty is often formulated as a stochastic optimization problem. In many settings, a "true" probability distribution may not be known, or the notion of a true distribution may not even be applicable. In this talk, we consider an approach, called distributionally robust stochastic optimization (DRSO), in which one hedges against all probability distributions that are within a chosen Wasserstein distance from a nominal distribution, for example an empirical distribution. Comparing to the popular phi-divergences, Wasserstein distance yields more reasonable worst-case distributions. We derive a dual reformulation of the corresponding DRSO problem and construct the worst-case distribution explicitly via the first-order optimality condition of the dual problem.
Our contributions are five-fold. (i) We identify necessary and sufficient conditions for the existence of a worst-case distribution, which are naturally related to the growth rate of the objective function. (ii) We show that the worst-case distributions resulting from an appropriate Wasserstein distance have a concise structure and a clear interpretation. (iii) Using this structure, we show that data-driven DRSO problems can be approximated to any accuracy by robust optimization problems, and thereby many DRSO problems become tractable by using tools from robust optimization. (iv) To the best of our knowledge, our proof of strong duality is the first constructive proof for DRSO problems, and we show that this technique is also useful in other contexts. (v) Our strong duality result holds in a very general setting, and can be applied to infinite dimensional process control problems and worst-case value-at-risk analysis.
This is a joint work with Anton Kleywegt.
Bio
Rui Gao is a 4th year PhD student in our department, working with Prof. Anton Kleywegt. His current research is focused on data-driven decision-making under uncertainty, arising in the context of revenue management, systems design and machine learning.
]]>
Abstract: Spatial regression is an important predictive tool in many scientific applications and an additive model provides a flexible regression relationship between predictors and a response variable. Such model is proved to be effective in regression based prediction. In this talk, we develop a regularized variable selection technique for building a spatial additive model. We found that the approaches developed for independent data do not work well for spatially dependent data. This motivates us to propose a spatially weighted L-2 error norm with a group LASSO type penalty to select additive components for spatial additive models. We establish the selection consistency of the proposed approach where the penalty parameter depends on several factors, such as the order of approximation of additive components, characteristics of the spatial weight and spatial dependence, etc. An extensive simulation study provides a vivid picture of the impacts of dependent data structures, the choice of a spatial weight as well as the asymptotic behavior of the estimates. We also investigate other regression models in the context of spatially dependent data.
Bio: Dr. Taps Maiti is currently serving as a Professor and Graduate Director in the Department of Statistics & Probability and the Co-director for the Center for Business and Social Analytics at Eli Broad College of Business at Michigan State University. His research interest is in application driven statistical theory and methods. He is a fellow of the American Statistical Association and Institute of Mathematical Statistics, has previously worked in several organizations: Iowa State University, U.S. Census Bureau, University of Nebraska- Lincoln and Harvard Medical School. His research has been published in all spectrums of statistical and applied sciences journals and supported by several federal funding. He has also served as an associate editor for several prestigious journals.
]]>
We welcome all ISyEgraduate students to submit abstracts for oral presentation and posters.
Topics of interest include but not limited to the SIAC core themes:
Systems monitoring, control and prognosis, fault diagnosis, quality engineering, DOE, big data, data mining, automation, advanced manufacturing, optimization
Eligibility for submission: ISyE Ph.D. students regardless of their track
Abstract submission deadline for oral presentations and posters: October 20th
For more information on the symposium please visit the official site:
http://pwp.gatech.edu/SIAC-Grad-Symposium/
Organizing committee: Murat Yildirim, SamanehEbrahimi, XiaoweiYue
Faculty advisor: Dr. Kamran Paynabar
Luncheon speaker: Dr. JianjunShi
“Identify promising research topics and publish in top journals”
For inquiries and questions please contact the chair: murat@gatech.edu
SIAC student symposium is a day-long event open to all students. We are focusing on promoting the research at the graduate level within ISyE. Our primary goals are i) to present the depth and breadth of research being pursued on the SIAC core themes to the first and second year students, and ii) to provide an opportunity for our senior students to disseminate their research findings through 20-minute oral presentations and posters.
Please register if you like to get lunch during the symposium, otherwise, feel free to stop by and attend the particular talks that rouse your interest.
SIAC graduate symposium will consist of oral presentations (20-minutes, similar format to their INFORMS counterparts), posters, and a luncheon address. This will be a unique opportunity to introduce some of the most exciting areas of research in our field to new graduate students. and for graduate students to rehearse and practice their talks.
If you wish to present your research or register for lunch, please visit our page: pwp.gatech.edu/siac-grad-symposium/. Please
]]>
Abstract
In most optimization models, the input parameters are uncertain estimates derived from data. Existing approaches in optimization focus on finding one optimal decision, to perform well on average, or to guarantee a worst-case performance under uncertainty. Although making a single decision given data is key to the operation of any system, additional insights as to how uncertain such solution might be is also important in decision-making. The intuition classical sensitivity analysis can provide is limited for complex systems because there can be a large number of input parameters. We propose a computational framework to empirically estimate the uncertainty by solving the optimization problem for sampled input parameters. In this talk, we focus on solving linear programs (LPs) with varying parameters.
The common approach is solving the LPs for all combinations of given parameter values, called the brute-force, which can be computationally infeasible when the parameter space is high-dimensional and/or the underlying LP is computationally challenging. We introduce a new approach for solving a large number of LPs that differ only in the right hand side of the constraints ($\bb$ of $\A x= \bb$). The computational approach builds on theoretical properties of the geometry of the space of critical regions, where a critical region is defined as the set of $\bb$'s for which a basis is optimal. To formally support our computational approach we provide proofs of geometric properties of neighboring critical regions. While these theoretical properties have been stated and applied in the existing literature of parametric programming, their formal proofs have not been provided to the best of our knowledge. Based on the geometric properties of critical regions, we develop an algorithm that solves the LPs in batches by finding critical regions that contain multiple $\bb$'s. Moreover, we suggest a data-driven version of our algorithm that uses the distribution (e.g., shape) of a sample of $\bb$'s for which the LPs need to be solved. The experimental results on a benchmark problem show that our approach can be more efficient and scale better in the number of $\bb$'s than the brute-force, but also indicate some limitations of the algorithm. Possible extensions of the method are also discussed.
Bio
Dr. Lee is a postdoc researcher in our department working with Dr. Serban. His research interests are in health data analytics and large-scale optimization problems arising in data analytics. He is applying his expertise in operations research and machine learning to translating large-scale health data into recommendations for policy makers and to develop novel approaches for solving optimization problems in healthcare applications.
]]>ISyE now has a BS/MS option for undergraduates where students may earn a BSIE and an MS Supply Chain Engineering (MSSCE) degree in 5 total years. We currently have 10-15 BSIE students in the program, intending to complete both degrees in 2017 or 2018.
Students admitted to the program transfer from undergraduate status to graduate status after fulfilling BSIE degree requirements at the end of a Fall semester, and must apply to the program either 1 year or 2 years prior to entering semester. Admitted students may begin taking graduate classes during the following Fall semester. Applications to the program are opening this week for students interested in completing the program in 2018 and 2019, and the application site will remain open until February 15, 2017. We seek strong students who meet Georgia Tech requirements for taking graduate classes while at the undergraduate level, and who are very interested in careers in the supply chain domain.
]]>We strongly encourage students to act now to seek full-time employment, internships, and projects (rather than waiting until the end of the semester). Plus, enjoy a free pizza lunch!
Where: ISyE Main Bldg, 2nd Floor Atrium
When: Wednesday, November 9, 10:30AM-1:30PM
What: The session will include:
Please plan on staying for the duration of the event and bring copies of your resume and business cards. Dress is business casual.
EVENT SPONSOR
The event is sponsored through the generosity and support of APICS - Atlanta Chapter. APICS is a non-profit educational organization addressing operations management and supply chain management issues, and providing professional development opportunities to its members. APICS Membership is free for full time students. Join today at www.apics.org/join and start networking at local APIC Atlanta events. Also make sure to stop by the APICS table at the event.
]]>]]>
ABSTRACT:
In the 1989 seminal paper, The boolean quadric polytope: Some characteristics, facets and relatives [Mathematical Programming, 45(1-3):139-172, 1989], Padberg introduced five classes of valid inequalities for the boolean quadric polytope: triangle, clique, cut, generalized cut, and odd cycle inequalities. In addition to the McCormick relaxation, these inequalities give a stronger relaxation of the convex hull of the graph of a bilinear function. In this talk, we study classes of bilinear functions where the McCormick relaxation and some of the Padberg inequalities characterize the convex hull. Furthermore, we study which of the Padberg inequalities give the strongest relaxation of the convex hull. We then apply the strong inequalities to (quadratically constrained) quadratic programs from the literature to find good lower bounds fast. Finally, we demonstrate that warm starting a global optimization solver with these lower bounds can improve the solver's performance.
This is joint work with Natashia Boland, Thomas Kalinowski, and Hamish Waterer.
]]>ABSTRACT:
Interactions and effect aliasing are among the fundamental concepts in experimental design. Some new insight and approach are given on this time honored subject. Start with the very simple two-level fractional factorial designs. Two interactions AB and CD are said to be aliased if both represent and are used to estimate the same effect. In the literature this aliasing is deemed impossible to be “de-aliased” or estimated. We argue that this “impossibility” can indeed be resolved by taking a new approach which consists of reparametrization using the notion of “conditional main effects” (cme’s) and model selection by exploiting the properties between the cme’s and traditional factorial effects. In some sense this is a shocking result as this has been taken for granted since the founding work of Finney (1945). There is a similar surprise for three-level fractional factorial designs. The standard approach is to use ANOVA to decompose the interactions into orthogonal components, each of 2-d. Then the quandary of full aliasing between interaction components remains. Again this can be resolved by using a non-orthogonal decomposition of the four degrees of freedom for AxB interaction using the linear-quadratic parametrization. Then a model search strategy would allow the estimation of some interaction components even for designs of resolution III and IV. Moving from regular to nonregular designs like the Plackett-Burman designs, most of the interactions are not orthogonal to the main effects. The partial aliasing of the effects and their complexity was traditionally viewed as “hazards”. Hamada and Wu (1992) recognized that this could be turned into an advantage. Their analysis strategy for effect de-aliasing is a precursor to what was described above. Underlying the three problems is the use of reparametrization and exploitation of non-orthogonality among some effects. The stated approach can be extended beyond designed experiments and potential applications in machine learning will be outlined.
(This internal talk is a repeat of the Akaike Memorial Lecture I gave on September 5 in Kanazawa, Japan.)
]]>ABSTRACT:
Motivated by the binary classification problem in machine learning, we study a class of decision problems where the decision maker has a list of goals, from which he aims to attain the maximal possible number of goals. In binary classification, this essentially means seeking a prediction rule to achieve the lowest probability of misclassification, and computationally it involves minimizing a (difficult) non-convex, 0-1 loss function. To address the intractability, previous methods consider minimizing the cumulative loss – the sum of convex surrogates of the 0-1 loss of each goal. We revisit this paradigm and develop instead an axiomatic framework by proposing a set of salient properties on functions for goal scoring and then propose the coherent loss approach, which is a tractable upper-bound of the loss over the entire set of goals. We show that the proposed approach yields a strictly tighter approximation to the total loss (i.e., the number of missed goal) than any convex cumulative loss approach while preserving the convexity of the underlying optimization problem. Moreover, this approach, applied to for binary classification, also has a robustness interpretation which builds a connection to robust SVMs.
Bio: Dr. Huan Xu is an assistant professor at the Stewart School of Industrial & Systems Engineering at Georgia Tech. His current research interest focuses on data, learning, and decision making. Specifically, he is interested in machine learning, high-dimensional statistics, robust and stochastic optimization, sequential decision making, and application to large-scale systems.
]]>
ABSTRACT:
Some statistical issues related to the monitoring of surgical outcome quality will be reviewed in this presentation. The important role of risk-adjustment in healthcare, used to account for variations in the health conditions of patients, will be described. Several of the methods for monitoring outcome quality over time, including a new one, will be outlined and illustrated with examples. The advantages of using the conditional false alarm rate metric will be emphasized.
References:
Steiner, S. H. and Woodall, W. H. (2016). “Debate: What is the Best Method to Monitor Surgical Performance?”, BMC Surgery. 16:15 DOI 10.1186/s12893-016-0131-8.
Woodall, W. H., Fogel, S. L., and Steiner, S. H. (2015). “The Monitoring and Improvement of Surgical Outcome Quality”. Journal of Quality Technology 47(4), 383-399.
Zhang, X. and Woodall, W. H. (2015). “Dynamic Probability Control Limits for Risk-adjusted Bernoulli CUSUM Charts”. Statistics in Medicine 34, 3336-3348.
Bio:
William H. Woodall, Professor of Statistics at Virginia Tech, is a former editor of the Journal of Quality Technology (2001–2003) and Associate Editor of Technometrics (1987–1995; 2013). He has published well over 140 papers, most on aspects of process monitoring and health-related surveillance. He is the recipient of the ASQ Shewhart Medal (2002), ENBIS Box Medal (2012), Jack Youden Prize (1995, 2003), ASQ Brumbaugh Award (2000, 2006), Ellis Ott Foundation Award (1987), Soren Bisgaard Award (2012), Lloyd S. Nelson Award (2014), and a best paper award from IIE Transactions on Quality and Reliability Engineering (1997). He is a Fellow of the American Statistical Association, a Fellow of the American Society for Quality, and an elected member of the International Statistical Institute.
]]>ABSTRACT:
Much of the literature on online optimization focuses on unconstrained minimization of objective functions with a large number of terms. We are interested in extending this development to create online algorithms for convex optimization problems with large numbers of constraints. We offer two approaches in this regard. First, we combine random constraint sampling with the classical primal-dual algorithm. Second, we combine random constraint sampling with classical penalty/barrier methods. We are able to give a convergence rate analysis for both approaches.
Bio
William B. Haskell completed his Ph.D in operations research at the University of California Berkeley in 2011. He is currently an assistant professor in the Department of Industrial and Systems Engineering at the National University of Singapore. His research focuses on large-scale decision-making, and he has a special interest in risk-aware sequential optimization.
]]>ABSTRACT:
Several important subproblems, such as switching machines on and off, finding an optimal convex set in 2-D, or buying and selling of a commodity, can be formulated as shortest/longest path problems in an acyclic graph. The corresponding polyhedron provides an implicit polynomial size description of the convex hull of solutions. A natural question is whether one can find a similar description in the original variables of the problem. In this talk we present several examples, each time using a different technique to obtain the projection. This is in large part joint work with Maurice Queyranne.
]]>ABSTRACT:
We will discuss how transport maps, i.e., deterministic couplings between probability measures, can enable useful new approaches to Bayesian computation. A first use involves a combination of optimal transport and Metropolis correction; here, we use continuous transportation to transform typical MCMC proposals into adapted non-Gaussian proposals, both local and global. Second, we discuss a variational approach to Bayesian inference that constructs a deterministic transport map from a reference distribution to the posterior, without resorting to MCMC. Independent and unweighted samples can then be obtained by pushing forward reference samples through the map.
Making either approach efficient in high dimensions, however, requires identifying and exploiting low-dimensional structure. We present new results relating the sparsity and decomposability of transports to the conditional independence structure of the target distribution. We also describe conditions, common in inverse problems, under which transport maps have a particular low-rank or near-identity structure. In general, these properties of transports can yield more efficient algorithms. As a particular example, we derive new deterministic "online" algorithms for Bayesian inference in nonlinear and non-Gaussian state-space models with static parameters.
This is joint work with Daniele Bigoni, Matthew Parno, and Alessio Spantini.
]]>
ABSTRACT:
We present an asynchronous algorithm for solving the stochastic unit commitment (SUC) problem using scenario decomposition. The algorithm is motivated by the scale of problem and significant differences in run times observed among scenario subproblems, which can result in inefficient use of distributed computing resources by synchronous parallel algorithms. Dual iterations are performed asynchronously using a block-coordinate subgradient descent method which allows performing block-coordinate updates using delayed information. We provide convergence guarantees for the asynchronous block-coordinate subgradient method based on previous results for incremental subgradient methods and stochastic subgradient methods. The algorithm recovers candidate primal solutions from the solutions of scenario subproblems using recombination heuristics.
The asynchronous algorithm is implemented in a high performance computing cluster and we conduct numerical experiments for two-stage SUC instances of the Western Electricity Coordinating Council (WECC) system and of the Central Western European (CWE) system. The WECC system that we study consist of 130 thermal generators, 182 nodes and 319 lines with hourly resolution and up to 1000 scenarios, while the CWE system consist of 656 thermal generators, 679 nodes and 1073 lines, with quarterly resolution and up to 120 scenarios. When using 10 nodes of the cluster per instance, the algorithm provides solutions that are within 2% of optimality to all problems within 47 minutes for WECC and 3 hours, 54 minutes for CWE. Moreover, we find that an equivalent synchronous parallel subgradient algorithm would leave processors idle up to 84% of the time, an observation which underscores the need for designing asynchronous optimization schemes in order to fully exploit distributed computing on real world applications.
Bio
Ignacio Aravena obtained his B.Sc. and M.Sc. degrees in Electrical Engineering from Universidad Tecnica Federico Santa Maria (UTFSM), Chile, where he also served as lecturer and as industrial consultant. He is currently a Ph.D. student on Applied Mathematics at Universite Catholique de Louvain (UCL), Belgium. His research focuses on evaluating the impact of renewable energy integration on the European electricity markets, by using detailed models and high performance computing.
]]>ABSTRACT:
Advanced Manufacturing is facing a new renaissance, due to the widespread of emerging process technologies (e.g., additive manufacturing, micro and nano-manufacturing) combined to a paradigm shift in sensing and computing. In this scenario, traditional approaches for intelligent data analysis (i.e., statistical data modeling, monitoring and control) need to be revised in order to deal with 3D quality features, multi-stream signal data, noncontact image point clouds. Starting from real industrial problems, some of the main challenges to be faced in these research fields are discussed. Viable solutions to enhance zero-defect manufacturing via in-line, in-situ statistical process monitoring are presented. Special attention is devoted to opportunities arising in metal Additve Manufacturing.
Bio:
Bianca Maria Colosimo is Professor in the Department of Mechanical Engineering of Politecnico di Milano, where she received her MSc and PhD in Industrial Engineering. She spent almost one year at the Pennsylvania State University (PSU) as a post-doc in 2001. Since then, she is cooperating with the Engineering Statistics Laboratory, directed by E. del Castillo (PSU).
Her research interest is mainly in the area of quality engineering (i.e. statistical process monitoring, control and optimization), with special attention to advanced manufacturing processes. On these topics, she is author of 100+ contributions, half of which have been published in peer-reviewed international journals and books. She is member of the Editorial Board of Journal of Quality Technology (American Society for Quality).
]]>
The Capstone Design Expo is one of the largest student design expos in the U.S. It is a showcase of Georgia Tech’s graduating seniors as they present their innovative projects designed and built during the Capstone Design Course. Students work in teams to solve either an industry problem, develop innovative tools to assist researchers or work on their own entrepreneurial idea.
Past expos have witnessed projects which have yielded significant results for our industry sponsors, saving some of them upwards of millions of dollars in research and development costs. The networking experience for students gives them the opportunity to make a lasting first impression on potential employers, while others have even walked away with an invitation to come and visit a potential employment opportunity with some of our sponsors.
ABSTRACT:
We consider the problem of sequential detection of a change in the statistical behavior of an observed process. After presenting a panorama of applications from diverse scientific fields that can be formulated as a sequential change detection problem, we introduce the various metrics adopted in the literature for the mathematical setup of the problem of interest. In each case we make a thorough overview of the existing optimum detection strategies, mention applications the formulation is suitable for, and pay particular attention to results that have been recently developed. Finally, we discuss versions of the problems that are still open and have been challenging researchers for many years.
BIO: George V. Moustakides received the diploma in Electrical and Mechanical Engineering from the National Technical University of Athens, Greece, the MSE in Systems Engineering from the Moore School of Electrical Engineering, University of Pennsylvania, Philadelphia, USA and the MSc and PhD in Electrical Engineering and Computer Science from Princeton University, Princeton, USA. Since 2007 he is with the department of Electrical and Computer Engineering, University of Patras, Greece while prior to this position he held long-term appointments as junior and senior researcher (directeur de recherche) with INRIA, France and as professor with the University of Thessaly, Greece. During his career Prof. Moustakides also held visiting scholar and/or adjunct professor positions at numerous universities in USA as Princeton University, University of Pennsylvania, Columbia University, University of Maryland, University of Illinois at Urbana-Champaign and recently Rutgers University. He has served as associate editor for Detection and Estimation (2011-2014) and is currently serving as inaugural associate editor for Sequential Methods (2016-2019) for the IEEE Transactions on Information Theory. His research focuses on Sequential Analysis and Statistical Signal Processing.
]]>
ABSTRACT:
Probabilistically constrained stochastic programs (PC-SPs) have many applications in science and engineering but are very challenging to solve. Furthermore, linear programming (LP) provides very weak bounds on the optimal value. In this talk, we introduce a new decomposition approach using irreducible infeasible subsystem (IIS) inequalities to strengthen the LP-relaxation of PC-SPs. We first establish the theoretical results for determining IIS inequalities for the continuous case, and then extend the results to the binary case and give example illustrations. Next, we present an IIS branch-and-cut algorithm for PC-SP and report on preliminary computational results.
Bio
Lewis Ntaimo received his Ph.D. degree in systems and industrial engineering in 2004, his M.S. degree in mining and geological engineering in 2000, and B.S. degree in mining engineering, all from the University of Arizona. He has been with Texas A&M University since 2004. Dr. Ntaimo research interests are in algorithms for large-scale stochastic optimization, systems modeling, and discrete event simulation. Recent applications include wildfire response planning, energy reduction in data centers, wind farm operations and maintenance, and patient and resource management in healthcare. His research has been funded by the National Science Foundation, Department of Homeland Security, and industry. Dr. Ntaimo is a member of INFORMS and IISE. He served as Vice Chair for the INFORMS Optimization Society from 2008-2010 and is now Vice President for the INFORMS Minority Issues Forum. He is on the Editorial Board of the Journal of Global Optimization is a member of the technical committee for the Society of Computer Simulation DEVS symposium.
]]>
ABSTRACT:
The National Science Foundation (NSF) is in the midst of a series of major, multi-directorate investments in the basic science and engineering underlying society's ability to prepare for--and respond to--hazards and disasters. This talk reviews recent results, opportunities and challenges in this area, focusing on strongly interdisciplinary research where humans are inextricably "in the loop." Examples are drawn from the Infrastructure Management and Extreme Events (IMEE) program, as well as from recently-released solicitation in Critical Resilient Infrastructure Systems and Processes (CRISP) and Smart and Connected Communities (S&CC). The talk will include ample opportunity for discussion.
David Mendonca currently directs the IMEE program at NSF and participates in the administration of a number of others. While at NSF, he is on leave from the Industrial and Systems Engineering Department at Rensselaer Polytechnic Institute, where he is an Associate Professor. His research focuses on the role of systems engineering in disaster response.
]]>
ABSTRACT:
The area of polynomial optimization has been actively studied for years, where the goal is to find a high-quality solution using an efficient computational method. Some of the important research problems in this area are: i) how does the underlying structure of an optimization problem affect its complexity? Ii) how does sparsity help? iii) how to find a near globally optimal solution whenever it is hard to find a global minimum? iv) how to design an efficient numerical algorithm for large-scale non-convex optimization problems? v) how to deal with problems with a mix of continuous and discrete variables? In this talk, we will develop a new mathematical framework to study the above problems. Our framework rests on recent advances in graph theory and optimization, including the notions of OS-vertex sequence and treewidth, matrix completion, semidefinite programming (SDP), and low-rank optimization.
As an application, we will study four fundamental mixed-integer power optimization problems, named power flow, security-constrained optimal power flow, state estimation and unit commitment. Power optimization problems are at the heart of the multi-billion electricity market and 1-5% improvements in their solutions lead to saving billions of dollars annually. The design of better optimization techniques for power systems has been an active area of research since 1962. In this talk, we will show that real-world power networks have low treewidth, and as a result their SDP relaxation always has a low-rank solution. By leveraging this property, we will design a penalized SDP relaxation to find a near-global solution. We will illustrate our results on real-world power grids with over 13,000 nodes described by nonlinear equations subject to noise and corrupted data.
Bio
Javad Lavaei is an Assistant Professor in the Department of Industrial Engineering and Operations Research at University of California, Berkeley. He was an Assistant Professor at Columbia University from 2012 to 2015. He received the Ph.D. degree in Control and Dynamical Systems from the California Institute of Technology in 2011, and was a postdoctoral scholar in Precourt Institute for Energy and Electrical Engineering at Stanford University in 2011-2012. He is the recipient of the Milton and Francis Clauser Doctoral Prize for the best university-wide Ph.D. thesis, entitled "Large-Scale Complex Systems: From Antenna Circuits to Power Grids". He researches on optimization theory, control theory and power systems. He has won several awards, including DARPA Young Faculty Award, Office of Naval Research Young Investigator Award, Office of Naval Research's Director of Research Early Career Award, Air Force Office of Scientific Research Young Investigator Award, National Science Foundation CAREER Award, Resonate Award, Google Faculty Research Award, Governor General of Canada Academic Gold Medal, Northeastern Association of Graduate Schools Master's Thesis Award, and Silver Medal in the 1999 International Mathematical Olympiad. Javad Lavaei is an associate editor of the IEEE Transactions on Smart Grid as well as the guest editor-in-chief of the IEEE Transactions on Smart Grid for a special issue on distributed computation, and serves on the conference editorial board of both IEEE Control Systems Society and European Control Association. He was a finalist (as an advisor) for the Best Student Paper Award at the 53rd IEEE Conference on Decision and Control 2014. His journal paper entitled "Zero Duality Gap in Optimal Power Flow Problem" has received a prize paper award given by the IEEE PES Power System Analysis Computing and Economics Committee in 2015. Javad Lavaei is a recipient of the 2015 INFORMS Optimization Society Prize for Young Researchers, the 2016 Donald P. Eckman Award given by the American Automatic Control Council, and the 2016 INFORMS ENRE Energy Best Publication Award.
]]>This course is designed to provide students with an understanding of the complexities of global trade, its impact on logistics, and key areas of concern for international logistics managers. Key topics are investigated such as: Incoterms, global trade compliance, harmonized tariff schedules, US import and export regulations, US Free Trade Agreements, and supply chain security.
Upon completion of this course, you will be able to:
WHAT IS COVERED
Participants receive a course notebook.
COURSE PREREQUISITES
None.
This course is part of the Supply Chain Management (SCM) Certificate.
On the first day, please check in at least 30 minutes before the class start time.
As supply chain executives become more instrumental in supporting long-term strategic objectives, they need to complement traditional supply chain operational knowledge with a more strategic view of their role in delivering aligned results to the business. Learn about different lenses of strategic planning applied to supply chain management and the specific implications on supply chain operations.
During the course, attendees will have several opportunities to assess their current supply chain strategy, formulate a new one, discuss about keys to implement a demand driven supply chain strategy, and how to review and align one.
For the duration of the course, participants will have the opportunity to work with an extended simulation game of a fictional company, and see the impact of supply chain strategic decisions in real time, while monitoring their ability to manage uncertainty and deliver financial results for the firm.
Those responsible for determining the future position of supply chain strategy, executing specific supply chain processes that must support specific business initiatives, innovating supply chain strategy to better align with operational goals, understanding the strategic impact of supply chain decisions in the firm and the extended enterprise network and advising clients about their specific supply chain strategic positioning.
Participants receive a course notebook.
None.
Laptop computer and calculator to be provided by the student.
This course is part of the Supply Chain Management (SCM) Certificate and can also be used towards the Strategic Sourcing and Supply Management (SSSM) Certificate.
On the first day, please check in at least 30 minutes before the class start time.
Supply Chain Management projects can span a wide range of project types including supply chain strategy, network analysis, facility design build, supply chain technology selection and implementation, and continuous process improvement initiatives. This course provides an overview of project management methodologies as applied in the supply chain environment. Class discussion and projects provide an understanding of how fundamental project management approaches and industry best practices can be used to effectively manage the complexities. Supply chain projects typically require managing resources, stakeholder alignment, risk management, customer impact, and effective communication across many internal and external business partners.
Upon completion of this course, you will be able to:
None.
For those interested in earning the Supply Chain Project Management Certificate, this course is the first of the four-course certificate program. To earn the certificate, participants must register and complete the following courses in the below sequence within four years, plus one elective.
For a list of courses that can be used as electives towards this certificate, please visit the Georgia Tech Professional Education website.
]]>RSVP: https://events.isye.gatech.edu/advance-media-savy-research
During this interactive workshop, experts from Institute Communications will discuss interviews with journalists (print, radio, TV and web) and writing op-eds. They will explain the services offered by Institute Communications, including formal media training. They will also talk about Institute opportunities to promote research -- the Amplifier expert blog, Research Horizons and the TECH+knowledge+Y video series -- and connect with a more general audience.
Presenters:
Laura DiamondMedia Relations Representative
|
Jason MadererMedia Relations Representative
|
John ToonDirector of Research News
|
Develop effective supply chain performance measurement processes to drive alignment across the corporation. Corporations often struggle with a lack of alignment between financial goals and operational metrics. Additionally, today’s information technology often overwhelms management with data and metrics. In this 3-day course you will learn how to develop metrics that synchronize supply chain and logistics metrics with key company financial metrics and goals. Through coursework and hands-on exercises, students learn to tailor metrics and measurement processes to focus on the most important aspects of the operations and overall corporate goals. As part of the course, performance dashboards from participating student companies and best-in-class organizations will be critiqued. The methods learned in the course are intended to be immediately put to use in the corporate environment.
Chief supply chain officers, executive vice presidents of supply chain, executive vice presidents of procurement, company owners, logistics service providers, consultants, vice presidents of sales operations, vice presidents/directors of process improvement, executive/senior/vice presidents/directors of supply chain, executive/senior/vice presidents/directors of logistics, executive/senior/vice presidents/directors of procurement, executive/senior/vice presidents/directors of manufacturing, executive/senior/vice presidents/directors of distribution
Upon completion of this course, you will be able to:
WHAT IS COVERED
Participants receive a course notebook.
COURSE PREREQUISITES
None.
This course is part of the Supply Chain Management (SCM) Certificate.
PROGRAM TIMES
On the first day, please check in at least 30 minutes before the class start time.
Supply Chain Management projects can span a wide range of project types including supply chain strategy, network analysis, facility design build, supply chain technology selection and implementation, and continuous process improvement initiatives. This course provides an overview of project management methodologies as applied in the supply chain environment. Class discussion and projects provide an understanding of how fundamental project management approaches and industry best practices can be used to effectively manage the complexities. Supply chain projects typically require managing resources, stakeholder alignment, risk management, customer impact, and effective communication across many internal and external business partners.
Upon completion of this course, you will be able to:
None.
For those interested in earning the Supply Chain Project Management Certificate, this course is the first of the four-course certificate program. To earn the certificate, participants must register and complete the following courses in the below sequence within four years, plus one elective.
For a list of courses that can be used as electives towards this certificate, please visit the Georgia Tech Professional Education website.
]]>This course focuses on defining, executing, and improving the S&OP process. Participants will be introduced to the appropriate stakeholders of S&OP, the importance of S&OP to corporate performance, S&OP cadence, and the use of visionary technology to bring S&OP to the next level. Business cases will be used to show concrete examples of companies where S&OP is effectively applied.
Upon completion of this course, you will be able to:
Participants receive a course notebook, an in-class software demonstration, and hand-out materials.
None.
Laptop computer by the student.
This course is part of the Supply and Demand Planning (SDP) Certificate.
PROGRAM TIMES
On the first day, please check in at least 30 minutes before the class start time.
This course provides a holistic view toward corporate profitability and supports effective complexity management. Participants will learn about the challenges of today's operating environment with "big data," cross-functional consensus and strategies that impact profitability. Integrated Business Planning (IBP) building blocks will be provided that solve these challenges. Break-out sessions will allow participants to apply these IBP concepts with an interactive tool.
Upon completion of this course, you will be able to:
Participants receive a course notebook and reading materials.
None.
Laptop computer by the student.
This course is part of the Supply and Demand Planning (SDP) Certificate.
PROGRAM TIMES
On the first day, please check in at least 30 minutes before the class start time.
Leading companies throughout the world are looking to formulate integrated supply strategies on both a local geographical and a global basis. This includes strategically sourcing materials and components worldwide and selecting global locations for key supply and distribution centers. The growth in global trade will continue to have a major impact on supply chains and requires firms to practice professional strategic supply management in order to help ensure continuity of supply and to contain and reduce costs.
Strategic sourcing enhances value, ultimately impacting the profitability of an entire organization. In this essential course, you’ll learn how to develop and implement a sourcing strategy that aligns with overall competitive strategy. The course and the associated case studies, activities and discussions provide the context and a framework for making effective sourcing decisions including a comprehensive approach to strategic sourcing.
Upon completion of this course, you will be able to:
Required
Provided
None.
No prerequisites. This course is part of the Supply Chain Management (SCM) Certificate.
]]>This course will demonstrate how warehouse operations are a key enabler to a successful supply chain implementation and the starting point for a transformation. It is critical to manage safety, quality and efficiency. Learn to leverage the lean supply chain modifications to improve customer responsiveness and reduce operating costs and in doing so contributing to a supply chain that creates a competitive advantage for a company. To accomplish this goal, we must bring lean principles into the warehouse and distribution center.
Supply chain professionals, logistics professionals, material managers, production control managers, transportation managers, warehousing managers and purchasing managers
Upon completion of this course, you will be able to:
Benefits:
Required
Provided
COURSE PREREQUISITES
None.
This course is part of the Distribution Operations Analysis and Design (DOAD) Certificate.
On the first day, please check in at least 30 minutes before the class start time.
In today’s global economy, operating risks are increasingly on the minds of executives. The specific context of operating risk can range from general areas of business continuity to the effects of natural disasters. In this course participants will gain a solid understanding of Supply Chain Risk Management principals including effective ways to identify, mitigate and measure the impact of potential supply chain disruptions.
Upon completion of this course, you will be able to:
Participants receive a course notebook, an in-class software demonstration, and hand-out materials.
No prerequisites. For those interested in earning the Supply and Demand Planning Certificate, take the below core courses and one elective course within four years. Please note that we are offering all three core courses in the series during the week of June 6, 2016 on the Georgia Tech campus.
Laptop computer by the student.
This course is part of the Supply and Demand Planning (SDP) Certificate.
PROGRAM TIMES
On the first day, please check in at least 30 minutes before the class start time.
Supply chain management and logistics encompasses all the activities involved in getting products to consumers including planning, storing, moving, and accounting for inventory. Inventory availability is the most important aspect of customer service, and the cost of inventory is one of the most important entries on a company's balance sheet.
Recognition of the balance sheet implications of inventory in supply chain management has launched a variety of industry-wide inventory reduction initiatives. Despite all these initiatives to reduce inventory in the supply chain, inventory levels for most companies have remained the same or increased. This course is focused on understanding how to efficiently provide the level of inventory that is really necessary for customer service while minimizing the inventory resulting from poor supply chain management.
Upon completion of this course, you will be able to:
Participants receive a course notebook.
None.
This course is part of the Supply Chain Management (SCM) Certificate and can also be used towards the Strategic Sourcing and Supply Management (SSSM) Certificate.
On the first day, please check in at least 30 minutes before the class start time.
This workshop provides an introduction to the field of material handling, including systems analysis, equipment selection, and the relationship of material handling to other activities and operations of the industrial plant or warehouse. It is also an excellent refresher course for those who want an update on the latest trends. You will learn how to plan and analyze material handling systems; how to improve material handling operations; and when to apply material handling automation. Key features are case examples and a guided exercise to ensure your mastery of the techniques presented.
Essential learning for those who are seeking cost reductions through better handling methods. Also valuable for those who must replace, upgrade, or add material handling equipment. The two-day course will include case examples and a guided exercise to ensure mastery of the techniques presented.
Material handling and logistics engineers, manufacturing and process engineers, industrial Engineers and systems analysts, production supervisors and team leaders, warehouse supervisors and team leaders, and cell planning and Lean Manufacturing teams
Upon completion of this course, you will be able to:
Participants receive a course notebook.
None.
This course is part of the Supply Chain Management (SCM) Certificate.
On the first day, please check in at least 30 minutes before the class start time.
The requirement for high levels of customer service, increasing numbers of SKUs and high labor costs have dramatically increased the complexity of warehouse operations. It is no longer sufficient to manage a warehouse based on a simple, arbitrary “ABC” classification of SKUs, which treats all those in a category as if they were identical. Instead, each decision – such as where to store or where to pick product – must be based on careful engineering and economic analysis. Each SKU must identify its own cheapest, fastest path through the warehouse to the customer and then compete with all the other SKUs for the necessary resources. This results in warehouse operations that are finely tuned to patterns of customer orders and maximally efficient. Learn the concepts necessary to address modern warehouse trade-offs between space and time in optimizing and managing your warehouse.
Essential learning for those who are seeking cost reductions through better handling methods. Also valuable for those who must replace, upgrade, or add material handling equipment. The two-day course will include case examples and a guided exercise to ensure mastery of the techniques presented.
Supply chain and logistics consultants, supply chain engineers and analysts, facility engineers, and warehouse supervisors and team leaders
Upon completion of this course, you will be able to:
Participants receive a course notebook.
None.
This course is part of the Supply Chain Management (SCM) Certificate.
On the first day, please check in at least 30 minutes before the class start time.
To become a lean supply chain professional, you need to first become a lean thinker and lean problem solver. This is the first course in a 3-course series on becoming a Lean Supply Chain professional. Students will be introduced to lean thinking and critical lean concepts. In addition, students will become proficient problem solvers through gained skills of waste identification and use of fundamental problem solving tools to eliminate waste at the root cause.
This first course is a pivot point in the educational process, and this is where current mental models and business paradigms will be challenged. Participants will learn to see operations from a new vantage point. Upon arrival back to the workplace, participants will be able to "talk" the talk of lean and also have a keen eye for operational waste. However, the real test of the first course is when the participant can "walk" the lean walk and solve business problems at the root cause, completely eliminating the problem for the organization.
Supply chain professionals, logistics professionals, material managers, production control managers, transportation managers, warehousing managers and purchasing managers
Day 1 - Lean Thinking
Day 2 - Fundamental Problem Solving
Day 3 - Sustaining Improvements
Post Classroom Training
Participants receive a course notebook.
None.
This is a required course for the Lean Supply Chain Professional (LSCP) Certificate and can also be used as an elective for the Supply Chain Management (SCM) Certificate.
On the first day, please check in at least 30 minutes before the class start time.
Effective planning of transportation and distribution networks has become more complex. This is driven by increasing customer requirements, expansion of global sourcing, security and regulatory requirements, volatile fuel costs, etc. This course is focused on understanding the strategic and tactical principles, practices, and tools required to address the cost, service, capacity, and carbon emissions tradeoffs in domestic and international transportation.
Executives and managers who want to learn about designing and operating best-in-class transportation and distribution for their supply chain, supply chain engineers and analysts, industrial engineers and systems analysts, supply chain and logistics consultants, transportation managers and engineers, and operations managers of traffic, transportation or warehousing
Upon completion of this course, you will be able to:
Participants receive a course notebook.
None.
This course is part of the Supply Chain Management (SCM) Certificate.
On the first day, please check in at least 30 minutes before the class start time.