{"560071":{"#nid":"560071","#data":{"type":"event","title":"ARC Colloquium: Ankur Moitra (MIT)","body":[{"value":"\u003Cp style=\u0022color:maroon;\u0022\u003EVideo of this talk is available at: \u003Ca href=\u0022https:\/\/smartech.gatech.edu\/handle\/1853\/56016\u0022\u003Ehttps:\/\/smartech.gatech.edu\/handle\/1853\/56016\u003C\/a\u003E\u003C\/p\u003E\r\nFull collection of talk videos are available at:  \r\n\u003Ca href=\u0022https:\/\/smartech.gatech.edu\/handle\/1853\/46836\u0022\u003Ehttps:\/\/smartech.gatech.edu\/handle\/1853\/46836\u003C\/a\u003E\r\n\r\n\u003Cbr\u003E\r\n\u003Cbr\u003E\r\n\r\n\u003Cp align=\u0022center\u0022\u003E\u003Cstrong\u003EAlgorithms \u0026amp; Randomness Center (ARC)\u003C\/strong\u003E\u003C\/p\u003E\r\n\r\n\u003Cp align=\u0022center\u0022\u003E\u003Ca href=\u0022http:\/\/people.csail.mit.edu\/moitra\/\u0022\u003E\u003Cstrong\u003EAnkur Moitra - MIT\u003C\/strong\u003E\u003C\/a\u003E\u003C\/p\u003E\r\n\r\n\u003Cp align=\u0022center\u0022\u003E\u003Cstrong\u003EMonday, October 31, 2016\u003C\/strong\u003E\u003C\/p\u003E\r\n\r\n\u003Cp align=\u0022center\u0022\u003E\u003Cstrong\u003EKlaus 1116 West \u0026ndash; 11:00 am\u003C\/strong\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003ETitle: \u003C\/strong\u003E\u003Cbr \/\u003E\r\nRobust Statistics, Revisited\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003EAbstract\u003C\/strong\u003E:\u003Cbr \/\u003E\r\nStarting from the seminal works of Tukey (1960) and Huber (1962), the field of robust statistics asks: Are there estimators that provable work in the presence of noise? The trouble is that all known provably robust estimators are also hard to compute in high-dimensions.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EHere, we study a basic problem in robust statistics, posed in various forms in the above works. Given corrupted samples from a high-dimensional Gaussian, are there efficient algorithms to accurately estimate its parameters? We give the first algorithms that are able to tolerate a constant fraction of corruptions that is independent of the dimension. Additionally, we give several more applications of our techniques to product distributions and various mixture models.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EThis is based on joint work with Ilias Diakonikolas, Jerry Li, Gautam Kamath, Daniel Kane and Alistair Stewart.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003EBio: \u003C\/strong\u003E\u003Cbr \/\u003E\r\nAnkur Moitra is the Rockwell International Assistant Professor in the Department of Mathematics at MIT and a Principal Investigator in the Computer Science and Artificial Intelligence Lab (CSAIL). The aim of his work is to bridge the gap between theoretical computer science and machine learning by developing algorithms with provable guarantees and foundations for reasoning about their behavior. He is a recipient of a Packard Fellowship, a Sloan Fellowship, an NSF CAREER Award, an NSF Computing and Innovation Fellowship and a Hertz Fellowship.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E","summary":null,"format":"limited_html"}],"field_subtitle":"","field_summary":"","field_summary_sentence":[{"value":"Revisiting Robust Statistics (Klaus 1116 West at 11am)"}],"uid":"27466","created_gmt":"2016-08-08 10:33:20","changed_gmt":"2017-04-13 21:15:12","author":"Dani Denton","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2016-10-31T12:00:00-04:00","event_time_end":"2016-10-31T13:00:00-04:00","event_time_end_last":"2016-10-31T13:00:00-04:00","gmt_time_start":"2016-10-31 16:00:00","gmt_time_end":"2016-10-31 17:00:00","gmt_time_end_last":"2016-10-31 17:00:00","rrule":null,"timezone":"America\/New_York"},"extras":[],"groups":[{"id":"70263","name":"ARC"},{"id":"47223","name":"College of Computing"},{"id":"50875","name":"School of Computer Science"}],"categories":[],"keywords":[{"id":"111051","name":"Algorithm and Randomness Center"},{"id":"4265","name":"ARC"}],"core_research_areas":[],"news_room_topics":[],"event_categories":[{"id":"1795","name":"Seminar\/Lecture\/Colloquium"}],"invited_audience":[{"id":"78761","name":"Faculty\/Staff"},{"id":"78771","name":"Public"},{"id":"78751","name":"Undergraduate students"},{"id":"174045","name":"Graduate students"}],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[{"value":"\u003Cp\u003EDani Denton\u003C\/p\u003E\r\n\r\n\u003Cp\u003Edenton at cc dot gatech dot edu\u003C\/p\u003E\r\n","format":"limited_html"}],"email":[],"slides":[],"orientation":[],"userdata":""}}}