{"487561":{"#nid":"487561","#data":{"type":"event","title":"Seminar - Paul Grigas","body":[{"value":"\u003Cp\u003ETITLE: Structure-Enhancing Algorithms for Statistical Learning Problems\u003C\/p\u003E\u003Cp\u003EABSTRACT:\u003C\/p\u003E\u003Cp\u003EFor 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.\u0026nbsp; In this talk, we discuss several scalable algorithms that directly promote \u003Cem\u003Ewell-structured \u003C\/em\u003Esolutions 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.\u0026nbsp; In the context of linear regression, we study several boosting algorithms \u2013 which directly promote sparse solutions \u2013 from the perspective of modern first-order methods in convex optimization.\u0026nbsp; 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.\u0026nbsp; 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.\u0026nbsp; For both problem contexts, we present computational results using datasets from microarray and recommender system applications.\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EBio\u003C\/strong\u003E\u003C\/p\u003E\u003Cp\u003EPaul Grigas is a fifth year Ph.D. student in Operations Research at MIT.\u0026nbsp; His research interests include large-scale convex optimization, statistical machine learning, and data-driven decision making.\u0026nbsp; Paul is also interested in applications in online advertising and data analytics, among other areas.\u0026nbsp; Paul was recently awarded the 2015 INFORMS Optimization Society Student Paper Prize, and he was the recipient of an NSF Graduate Research Fellowship.\u0026nbsp; Before coming to MIT, Paul earned a B.S. in Operations Research and Information Engineering from Cornell University.\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E","summary":null,"format":"limited_html"}],"field_subtitle":"","field_summary":"","field_summary_sentence":[{"value":"Seminar - Paul Grigas"}],"uid":"27187","created_gmt":"2016-01-19 11:26:23","changed_gmt":"2017-04-13 21:17:03","author":"Anita Race","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2016-01-25T10:00:00-05:00","event_time_end":"2016-01-25T10:00:00-05:00","event_time_end_last":"2016-01-25T10:00:00-05:00","gmt_time_start":"2016-01-25 15:00:00","gmt_time_end":"2016-01-25 15:00:00","gmt_time_end_last":"2016-01-25 15:00:00","rrule":null,"timezone":"America\/New_York"},"extras":[],"groups":[{"id":"1242","name":"School of Industrial and Systems Engineering (ISYE)"}],"categories":[],"keywords":[],"core_research_areas":[],"news_room_topics":[],"event_categories":[{"id":"1795","name":"Seminar\/Lecture\/Colloquium"}],"invited_audience":[{"id":"78751","name":"Undergraduate students"},{"id":"78761","name":"Faculty\/Staff"},{"id":"174045","name":"Graduate students"}],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[],"email":[],"slides":[],"orientation":[],"userdata":""}}}