{"651572":{"#nid":"651572","#data":{"type":"event","title":"ARC Colloquium: Vidya  Muthukumar (Georgia Tech)","body":[{"value":"\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\u003Cstrong\u003EVidya Muthukumar (Georgia Tech)\u003C\/strong\u003E\u003C\/p\u003E\r\n\r\n\u003Cp align = \u0022center\u0022\u003E\u003Cstrong\u003EMonday, October 25, 2021\u003C\/strong\u003E\u003C\/p\u003E\r\n\r\n\u003Cp align = \u0022center\u0022\u003E\u003Cstrong\u003EGroseclose 402 - 11:00 am\u003C\/strong\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003ETitle:\u0026nbsp; \u003C\/strong\u003ESurprises in high-dimensional linear classification\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003EAbstract: \u003C\/strong\u003ESeemingly counter-intuitive phenomena in deep neural networks and kernel methods have prompted a recent re-investigation of classical machine learning methods, like linear models. Of particular focus is sufficiently high-dimensional setups in which\u0026nbsp;\u003Cem\u003Einterpolation\u003C\/em\u003E\u0026nbsp;of training data is possible. In this talk, we will first briefly review recent works showing that zero regularization, or fitting of noise, need not be harmful in regression tasks. Then, we will use this insight to uncover two new surprises for high-dimensional linear classification:\u003C\/p\u003E\r\n\r\n\u003Cul\u003E\r\n\t\u003Cli\u003Eleast-2-norm interpolation can classify consistently even when the corresponding regression task fails, and\u003C\/li\u003E\r\n\t\u003Cli\u003Ethe support-vector-machine and least-2-norm interpolation solutions \u003Cem\u003Eexactly coincide\u003C\/em\u003E in sufficiently high-dimensional linear model.\u003C\/li\u003E\r\n\u003C\/ul\u003E\r\n\r\n\u003Cp\u003EThese findings taken together imply that the linear SVM can generalize well in settings beyond those predicted by training-data-dependent complexity measures.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EThis is joint work with Misha Belkin, Daniel Hsu, Adhyyan Narang, Anant Sahai, Vignesh Subramanian, Christos Thrampoulidis, Ke Wang and Ji Xu.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E----------------------------------\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Ca href=\u0022https:\/\/www.isye.gatech.edu\/users\/vmuthukumar\u0022\u003ESpeaker\u0026#39;s Webpage\u003C\/a\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cem\u003EVideos of recent talks are available at: \u003C\/em\u003E\u003Ca href=\u0022https:\/\/smartech.gatech.edu\/handle\/1853\/46836\u0022\u003E\u003Cem\u003Ehttps:\/\/smartech.gatech.edu\/handle\/1853\/46836\u003C\/em\u003E\u003C\/a\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Ca href=\u0022https:\/\/mailman.cc.gatech.edu\/mailman\/listinfo\/arc-colloq\u0022\u003E\u003Cem\u003EClick here to subscribe to the seminar email list: arc-colloq@Klauscc.gatech.edu \u003C\/em\u003E\u003C\/a\u003E\u003C\/p\u003E\r\n","summary":null,"format":"limited_html"}],"field_subtitle":"","field_summary":"","field_summary_sentence":[{"value":"Surprises in high-dimensional linear classification - Groseclose 402 at 11am"}],"uid":"27544","created_gmt":"2021-10-11 14:14:28","changed_gmt":"2021-10-19 16:29:20","author":"Francella Tonge","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2021-10-25T12:00:00-04:00","event_time_end":"2021-10-25T13:00:00-04:00","event_time_end_last":"2021-10-25T13:00:00-04:00","gmt_time_start":"2021-10-25 16:00:00","gmt_time_end":"2021-10-25 17:00:00","gmt_time_end_last":"2021-10-25 17:00:00","rrule":null,"timezone":"America\/New_York"},"extras":[],"groups":[{"id":"70263","name":"ARC"}],"categories":[],"keywords":[],"core_research_areas":[],"news_room_topics":[],"event_categories":[{"id":"1795","name":"Seminar\/Lecture\/Colloquium"}],"invited_audience":[{"id":"78761","name":"Faculty\/Staff"},{"id":"177814","name":"Postdoc"},{"id":"174045","name":"Graduate students"},{"id":"78751","name":"Undergraduate students"}],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[],"email":[],"slides":[],"orientation":[],"userdata":""}}}