{"647155":{"#nid":"647155","#data":{"type":"event","title":"ML Ph.D. Proposal - Alejandro Carderera","body":[{"value":"\u003Cp\u003EYou are kindly invited to attend my Ph.D. proposal presentation. Please see the details below.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Ch4\u003E\u003Cstrong\u003ETitle:\u0026nbsp;Local Acceleration of the Frank-Wolfe Algorithm\u003C\/strong\u003E\u003C\/h4\u003E\r\n\r\n\u003Cp\u003EDate: May 11, 2021\u003C\/p\u003E\r\n\r\n\u003Cp\u003ETime:\u0026nbsp;10:00 AM EST\u003C\/p\u003E\r\n\r\n\u003Cp\u003ELocation:\u0026nbsp;\u003Ca href=\u0022https:\/\/bluejeans.com\/870141711\u0022\u003Ehttps:\/\/bluejeans.com\/870141711\u003C\/a\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Ch4\u003E\u003Cstrong\u003EAlejandro Carderera\u003C\/strong\u003E\u003C\/h4\u003E\r\n\r\n\u003Cp\u003EMachine Learning Ph.D. Student\u003C\/p\u003E\r\n\r\n\u003Cp\u003ESchool of Industrial and Systems Engineering\u003Cbr \/\u003E\r\nGeorgia Institute of Technology\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Ca href=\u0022https:\/\/alejandro-carderera.github.io\/\u0022\u003Ehttps:\/\/alejandro-carderera.github.io\/\u003C\/a\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Ch4\u003E\u003Cstrong\u003ECommittee\u003C\/strong\u003E\u003C\/h4\u003E\r\n\r\n\u003Cp\u003ESebastian Pokutta (Advisor)\u003C\/p\u003E\r\n\r\n\u003Cp\u003EGuanghui (George) Lan\u003C\/p\u003E\r\n\r\n\u003Cp\u003ESwati Gupta\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Ch4\u003E\u003Cstrong\u003EAbstract\u003C\/strong\u003E\u003C\/h4\u003E\r\n\r\n\u003Cp\u003EConditional Gradient (CG) algorithms are an important class of constrained optimization algorithms that eschew the need for projections, relying instead on linear programming oracles to ensure feasibility. In this proposal, we present two algorithms from this family, both of which show improved local convergence rates in the vicinity of the optimum when minimizing smooth and strongly convex functions. The first one, dubbed Locally Accelerated Conditional Gradients uses first-order information about the function and has a local linear convergence over polytopes that improves over that of existing CG-variants. The second algorithm, the Second Order Conditional Gradient Sliding algorithm (inspired by the Conditional Gradient Sliding algorithm), uses second-order information to obtain local quadratic convergence over polytopes under a set of assumptions.\u003C\/p\u003E\r\n","summary":null,"format":"limited_html"}],"field_subtitle":"","field_summary":"","field_summary_sentence":[{"value":"Alejandro Carderera will present his machine learning Ph.D. proposal."}],"uid":"34773","created_gmt":"2021-05-04 17:51:27","changed_gmt":"2021-05-04 17:51:27","author":"ablinder6","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2021-05-11T11:00:00-04:00","event_time_end":"2021-05-11T13:00:00-04:00","event_time_end_last":"2021-05-11T13:00:00-04:00","gmt_time_start":"2021-05-11 15:00:00","gmt_time_end":"2021-05-11 17:00:00","gmt_time_end_last":"2021-05-11 17:00:00","rrule":null,"timezone":"America\/New_York"},"extras":[],"groups":[{"id":"576481","name":"ML@GT"}],"categories":[],"keywords":[],"core_research_areas":[],"news_room_topics":[],"event_categories":[{"id":"1788","name":"Other\/Miscellaneous"}],"invited_audience":[{"id":"78761","name":"Faculty\/Staff"},{"id":"177814","name":"Postdoc"},{"id":"78771","name":"Public"},{"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":""}}}