{"43361":{"#nid":"43361","#data":{"type":"event","title":"Efficient Methods for Stochastic Composite Optimization","body":[{"value":"\u003Cp\u003E\u003Cstrong\u003ETITLE:\u003C\/strong\u003E  Efficient Methods for Stochastic Composite Optimization\n\u003C\/p\u003E\n\u003Cp\u003E\u003Cstrong\u003ESPEAKER:\u003C\/strong\u003E  Guanghui Lan\n\u003C\/p\u003E\n\u003Cp\u003E\u003Cstrong\u003EABSTRACT:\u003C\/strong\u003E\n\u003C\/p\u003E\n\u003Cp\u003EWe consider an important class of convex programming problems whose objective functions, given by the summation of a smooth and non-smooth component, are contaminated by stochastic noise. Although a valid lower bound on the rate of convergence for solving these problems is known from the classic complexity theory of convex programming due to Nemirovski and Yudin, the optimization algorithms that can achieve this lower bound have not been discovered. In this talk, we show that the robust stochastic approximation method exhibits the best-known rate of convergence for solving these problems. The main goal is to present the first theoretically optimal method for solving this class of problems that achieves the aforementioned lower bound on the rate of convergence and demonstrate its significant advantages over existing algorithms. \u003C\/p\u003E","summary":null,"format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"Efficient Methods for Stochastic Composite Optimization","format":"limited_html"}],"field_summary_sentence":[{"value":"Efficient Methods for Stochastic Composite Optimization"}],"uid":"27187","created_gmt":"2009-10-12 20:37:56","changed_gmt":"2016-10-08 01:47:38","author":"Anita Race","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2008-10-07T16:00:00-04:00","event_time_end":"2008-10-07T17:00:00-04:00","event_time_end_last":"2008-10-07T17:00:00-04:00","gmt_time_start":"2008-10-07 20:00:00","gmt_time_end":"2008-10-07 21:00:00","gmt_time_end_last":"2008-10-07 21:00:00","rrule":null,"timezone":"America\/New_York"},"extras":[],"groups":[{"id":"1242","name":"School of Industrial and Systems Engineering (ISYE)"}],"categories":[],"keywords":[{"id":"5682","name":"Convex programming"}],"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\u003EAnita  Race\u003C\/strong\u003E\u003Cbr \/\u003EH. Milton Stewart School of Industrial and Systems Engineering\u003Cbr \/\u003E\u003Ca href=\u0022http:\/\/www.gatech.edu\/contact\/index.html?id=ar9\u0022\u003EContact Anita  Race\u003C\/a\u003E","format":"limited_html"}],"email":[],"slides":[],"orientation":[],"userdata":""}}}