{"655069":{"#nid":"655069","#data":{"type":"event","title":"ARC Colloquium: Manolis Vlatakis (Columbia)","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\u003EManolis Vlatakis (Columbia)\u003C\/strong\u003E\u003C\/p\u003E\r\n\r\n\u003Cp align = \u0022center\u0022\u003E\u003Cstrong\u003EMonday, February 7, 2022\u003C\/strong\u003E\u003C\/p\u003E\r\n\r\n\u003Cp align = \u0022center\u0022\u003E\u003Cstrong\u003EVirtual via BlueJeans - 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\u003E Building Optimization beyond Minimization: A Journey in Game Dynamics\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003EAbstract:\u003C\/strong\u003E\u0026nbsp; Motivated by recent advances in both theoretical and applied aspects of multiplayer games, spanning from e-sports to multi-agent generative adversarial networks, a surge of different studies\u0026nbsp;have been focused on the core problem of\u0026nbsp;understanding the behavior of game dynamics in general\u0026nbsp;N-player games. From the seminal settings of two competitive players and Min-Max Optimization to the complete\u0026nbsp;understanding of how the day-to-day behavior of the dynamics correlates to the game\u0026#39;s different notion of equilibria is much more limited, and only partial results are known for certain classes of games (such as zero-sum or congestion games). In this talk, we study from two different perspectives\u0026nbsp;arguably the most well-studied class of no-regret dynamics, \u0026quot;Follow-the-regularized-leader\u0026quot; (FTRL) and Discretizations of Gradient Flow (GDA\/OGDA\/EG), \u0026nbsp;and we establish a sweeping negative result showing that the notion of mixed Nash equilibrium is antithetical to no-regret learning. Specifically, we show that any Nash equilibrium which is not strict (in that every player has a unique best response) cannot be stable and attracting under the dynamics of FTGL. This result has significant implications for predicting the outcome of a learning process as it shows unequivocally that only strict (and hence, pure) Nash equilibria can emerge as stable limit points thereof. For a final happy end story, we present either structural examples of families where convergence is possible providing the last-iterate convergence rates or even new methods inspired from other areas like control theory \u0026amp; planning.\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003EBio:\u003Cbr \/\u003E\r\nEmmanouil (Manolis) V. Vlatakis Gkaragkounis is a final year PhD student in the Department of Computer Science at Columbia University, under the supervision of prof. Mihalis Yannakakis and Rocco Servedio. Currently, he is Simons-Google Research fellow at the University of California at Berkeley.\u0026nbsp;Before joining Columbia University, he interned at \u0026quot;Athena\u0026quot; Research \u0026amp; Innovation Center in Athens, Greece. He received his integrated B.s \u0026amp; M.s in ECE Department of National Technical University of Athens, where he was advised by Dimitris Fotakis. Manolis\u0026#39;s primary interest is in the intersection of Theoretical Computer Science \u0026amp; Machine Learning, with a particular focus in\u0026nbsp;Algorithmic Game Theory, Optimization, Computational Complexity and Beyond Worst-case Analysis of Algorithms .\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E----------------------------------\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Ca href=\u0022http:\/\/www.cs.columbia.edu\/~emvlatakis\/\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":" Building Optimization beyond Minimization: A Journey in Game Dynamics - Virtual via BlueJeans at 11am"}],"uid":"27544","created_gmt":"2022-02-02 16:30:31","changed_gmt":"2022-02-04 18:17:18","author":"Francella Tonge","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2022-02-07T11:00:00-05:00","event_time_end":"2022-02-07T12:00:00-05:00","event_time_end_last":"2022-02-07T12:00:00-05:00","gmt_time_start":"2022-02-07 16:00:00","gmt_time_end":"2022-02-07 17:00:00","gmt_time_end_last":"2022-02-07 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":""}}}