{"44591":{"#nid":"44591","#data":{"type":"event","title":"Large-scale stochastic approximation proceedures","body":[{"value":"\u003Cp\u003E\u003Cstrong\u003EAdaptive Gain Choice for Large-Scale Stochastic Approximation Procedures\u003C\/strong\u003E\n\u003C\/p\u003E\n\u003Cp\u003EGUEST LECTURER\u003Cbr \/\u003E\nProf. Anatoli Iouditski\n\u003C\/p\u003E\n\u003Cp\u003EAFFILIATION\u003Cbr \/\u003E\nUniversity Joseph Fourier, Grenoble, France\n\u003C\/p\u003E\n\u003Cp\u003EABSTRACT\u003Cbr \/\u003E\nThe subject of this talk is a complexity analysis of a family of large-scale stochastic approximation algorithms. The methods belongs to the family of primal-dual descent algorithms, introduced by Yu. Nesterov. We propose an adaptive choice of the gain sequences of the algorithm which make it possible to attain the optimal rates of convergence on wide classes of problems. We show, for instance, that if it is known a priori that the objective function is Lipschitz, the proposed algorithm attains minimax rate of convergence. Further, if the objective belongs to a \u0022better class\u0022 of smooth functions with Lipschitz-continuous gradient, the proposed algorithm also attains the minimax rate.\u003C\/p\u003E","summary":null,"format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"Adaptive gain choice for large-scale stochastic approximation procedures.  \nThe subject of this talk is a complexity analysis of a family of large-scale stochastic approximation algorithms. The methods belongs to the family of primal-dual descent algorit","format":"limited_html"}],"field_summary_sentence":[{"value":"Large-scale stochastic approximation proceedures"}],"uid":"27216","created_gmt":"2009-10-12 21:22:58","changed_gmt":"2016-10-08 01:48:27","author":"Ruth Gregory","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2007-01-16T10:00:00-05:00","event_time_end":"2007-01-16T11:00:00-05:00","event_time_end_last":"2007-01-16T11:00:00-05:00","gmt_time_start":"2007-01-16 15:00:00","gmt_time_end":"2007-01-16 16:00:00","gmt_time_end_last":"2007-01-16 16:00:00","rrule":null,"timezone":"America\/New_York"},"extras":[],"groups":[{"id":"1242","name":"School of Industrial and Systems Engineering (ISYE)"}],"categories":[],"keywords":[{"id":"6425","name":"Adaptive gain choice"},{"id":"6426","name":"large-scale stochastic approximation procedures"}],"core_research_areas":[],"news_room_topics":[],"event_categories":[{"id":"1795","name":"Seminar\/Lecture\/Colloquium"}],"invited_audience":[],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[{"value":"\u003Cstrong\u003EArkadi  Nemirovski\u003C\/strong\u003E\u003Cbr \/\u003EISyE\u003Cbr \/\u003E\u003Ca href=\u0022mailto:arkadi.nemirovski@isye.gatech.edu\u0022\u003EContact Arkadi  Nemirovski\u003C\/a\u003E\u003Cbr \/\u003E\u003Cstrong\u003E404-894-2300\u003C\/strong\u003E","format":"limited_html"}],"email":[],"slides":[],"orientation":[],"userdata":""}}}