{"663102":{"#nid":"663102","#data":{"type":"event","title":"PhD Defense by Namjoon Suh","body":[{"value":"\u003Cp\u003E\u003Cstrong\u003ETitle:\u0026nbsp;Statistical Viewpoints on network modeling and deep learning\u003C\/strong\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003EDate:\u003C\/strong\u003E\u003Cstrong\u003E\u0026nbsp;Nov 18\u003Csup\u003Eth\u003C\/sup\u003E\u0026nbsp;, 2022\u003C\/strong\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003ETime:\u003C\/strong\u003E\u003Cstrong\u003E\u0026nbsp;8:00 - 9:00 AM EST\u003C\/strong\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003EMeeting Link:\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Ca href=\u0022https:\/\/gatech.zoom.us\/j\/8833061674\u0022\u003Ehttps:\/\/gatech.zoom.us\/j\/8833061674\u003C\/a\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003ENamjoon Suh\u003C\/strong\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003EMachine Learning PhD Student\u003C\/p\u003E\r\n\r\n\u003Cp\u003ESchool of Industrial \u0026amp; Systems Engineering\u003Cbr \/\u003E\r\nGeorgia Institute of Technology\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003ECommittee\u003C\/strong\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E1 Dr. Huo, Xiaoming (Advisor, ISyE, Gatech)\u003C\/p\u003E\r\n\r\n\u003Cp\u003E2 Dr. Mei, Yajun (Co-advisor, ISyE, Gatech)\u003C\/p\u003E\r\n\r\n\u003Cp\u003E3 Dr. Kang, Sung ha (Mathematics, Gatech)\u003C\/p\u003E\r\n\r\n\u003Cp\u003E4 Dr. Zhilova, Mayya\u0026nbsp;(Mathematics, Gatech )\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E5 Dr. Zhou, Ding-Xuan (School of Mathematics and Statistics, The university of Sydney)\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003EAbstract\u003C\/strong\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003EIn my thesis presentation, two of my works will be presented: \u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Col\u003E\r\n\t\u003Cli\u003E\u003Cstrong\u003EA new statistical model for network data\u003C\/strong\u003E :\u0026nbsp;We propose a combined model, which integrates the latent factor model and a sparse graphical model, for network data. It is noticed that neither a latent factor model nor a sparse graphical model alone may be sufficient to capture the structure of the data. The proposed model has a latent (i.e., factor analysis) model to represent the main trends (a.k.a., factors), and a sparse graphical component that captures the remaining ad-hoc dependence. Model selection and parameter estimation are carried out simultaneously via a penalized likelihood approach. The convexity of the objective function allows us to develop an efficient algorithm, while the penalty terms push towards low-dimensional latent components and a sparse graphical structure. The effectiveness of our model is demonstrated via simulation studies, and the model is also applied to four real datasets: Zachary\u0026#39;s Karate club data,\u0026nbsp; Kreb\u0026#39;s U.S. political book dataset (\u003Ca href=\u0022http:\/\/www.orgnet.com\u0022\u003Ehttp:\/\/www.orgnet.com\u003C\/a\u003E), U.S. political blog dataset, and citation network of statisticians; showing meaningful performances in practical situations.\u0026nbsp;\u003C\/li\u003E\r\n\t\u003Cli\u003E\u0026nbsp;\u003C\/li\u003E\r\n\t\u003Cli\u003E\u003Cstrong\u003ENew insights in approximation theory and statistical learning rate of deep ReLU network\u003C\/strong\u003E: This work provides the rigorous theoretical analysis on how the approximation rate and learning rate (i.e., excess risk) behave when deep ReLU fully connected network is used as a function approximator (estimator) when ground-truth functions are assumed to be in Sobolev spaces defined over unit sphere. With the help of spherical harmonic basis, we track the explicit dependence on data dimension d in the rates and prove that deep ReLU net can avoid \u0026ldquo;the curse of dimensionality\u0026rdquo; when the function smoothness is in the order d as d tends to infinity. This discovery is not something observed in the state-of-the-art result in deep learning theory; specifically, when the function is defined on d-dimensional cube, or convolutional neural networks are used as the function approximator. \u0026nbsp;\u0026nbsp;\u003C\/li\u003E\r\n\u003C\/ol\u003E\r\n","summary":null,"format":"limited_html"}],"field_subtitle":"","field_summary":"","field_summary_sentence":[{"value":"Statistical Viewpoints on network modeling and deep learning"}],"uid":"27707","created_gmt":"2022-11-11 17:01:57","changed_gmt":"2022-11-11 17:02:19","author":"Tatianna Richardson","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2022-11-18T09:00:00-05:00","event_time_end":"2022-11-18T11:00:00-05:00","event_time_end_last":"2022-11-18T11:00:00-05:00","gmt_time_start":"2022-11-18 14:00:00","gmt_time_end":"2022-11-18 16:00:00","gmt_time_end_last":"2022-11-18 16:00:00","rrule":null,"timezone":"America\/New_York"},"extras":[],"groups":[{"id":"221981","name":"Graduate Studies"}],"categories":[],"keywords":[{"id":"100811","name":"Phd Defense"}],"core_research_areas":[],"news_room_topics":[],"event_categories":[{"id":"1788","name":"Other\/Miscellaneous"}],"invited_audience":[{"id":"78761","name":"Faculty\/Staff"},{"id":"78771","name":"Public"},{"id":"78751","name":"Undergraduate students"}],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[],"email":[],"slides":[],"orientation":[],"userdata":""}}}