{"604683":{"#nid":"604683","#data":{"type":"event","title":"ML@GT Seminar: Mike Rabbat","body":[{"value":"\u003Cp\u003E\u003Cstrong\u003EBio:\u003C\/strong\u003E Mike Rabbat is a Research Scientist in the Facebook AI Research group. He is currently on leave from McGill University where he is an Associate Professor of Electrical and Computer Engineering. Mike received a Masters from Rice University in 2003 and a PhD from the University of Wisconsin in 2006, both under the supervision of Robert Nowak. Mike\u0026rsquo;s research interests are in the areas of networks, statistical signal\u0026nbsp;\u0026nbsp;\u0026nbsp;\u0026nbsp;\u0026nbsp;\u0026nbsp;\u0026nbsp;\u0026nbsp;\u0026nbsp;\u0026nbsp;\u0026nbsp; processing, and machine learning. Currently, he is working on gossip algorithms for distributed processing, distributed tracking, and algorithms and theory for signal processing on graphs.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003ETitle:\u003C\/strong\u003E Asynchronous Subgradient-Push\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003EAbstract:\u003C\/strong\u003E We consider a multi-agent framework for distributed optimization where each agent in the network has access to a local convex function and the collective goal is to achieve consensus on the parameters that minimize the sum of the agents\u0026#39; local functions.\u0026nbsp; We propose an algorithm wherein each agent operates asynchronously and independently of the other agents in the network. When the local functions are strongly-convex with Lipschitz-continuous gradients, we show that a subsequence of the iterates at each agent converges to a neighbourhood of the global minimum, where the size of the neighbourhood depends on the degree of asynchrony in the multi-agent network. When the agents work at the same rate, convergence to the global minimizer is achieved. Numerical experiments demonstrate that Asynchronous Subgradient-Push can minimize the global objective faster than state-of-the-art synchronous first-order methods, is more robust to failing or stalling agents, and scales better with the network size. This is joint work with Mahmoud Assran.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n","summary":null,"format":"limited_html"}],"field_subtitle":"","field_summary":"","field_summary_sentence":[{"value":"Please join us for a talk from Mr. Mike Rabbat"}],"uid":"34471","created_gmt":"2018-04-04 14:16:08","changed_gmt":"2018-04-04 14:17:55","author":"Kyla J. Reese","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2018-04-04T13:00:00-04:00","event_time_end":"2018-04-04T14:30:00-04:00","event_time_end_last":"2018-04-04T14:30:00-04:00","gmt_time_start":"2018-04-04 17:00:00","gmt_time_end":"2018-04-04 18:30:00","gmt_time_end_last":"2018-04-04 18:30:00","rrule":null,"timezone":"America\/New_York"},"extras":[],"hg_media":{"585217":{"id":"585217","type":"image","title":"Machine Learning","body":null,"created":"1482167801","gmt_created":"2016-12-19 17:16:41","changed":"1482167801","gmt_changed":"2016-12-19 17:16:41","alt":"Machine Learning","file":{"fid":"223118","name":"lower_banner.jpg","image_path":"\/sites\/default\/files\/images\/lower_banner.jpg","image_full_path":"http:\/\/tlwarc.hg.gatech.edu\/\/sites\/default\/files\/images\/lower_banner.jpg","mime":"image\/jpeg","size":104921,"path_740":"http:\/\/tlwarc.hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/images\/lower_banner.jpg?itok=rGFfJGZd"}}},"media_ids":["585217"],"groups":[{"id":"576481","name":"ML@GT"}],"categories":[],"keywords":[],"core_research_areas":[],"news_room_topics":[],"event_categories":[],"invited_audience":[{"id":"78761","name":"Faculty\/Staff"},{"id":"78771","name":"Public"},{"id":"78751","name":"Undergraduate students"}],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[{"value":"\u003Cp\u003EKyla Hanson: khanson@cc.gatech.edu\u003C\/p\u003E\r\n","format":"limited_html"}],"email":[],"slides":[],"orientation":[],"userdata":""}}}