{"622929":{"#nid":"622929","#data":{"type":"event","title":"ML@GT Fall Seminar: Galen Reeves, Duke University","body":[{"value":"\u003Cp\u003EThe Machine Learning Center at Georgia Tech invites you to a seminar by\u0026nbsp;Galen Reeves, an assistant professor from Duke University.\u003C\/p\u003E\r\n\r\n\u003Cp\u003ERSVP:\u0026nbsp;\u003Ca href=\u0022http:\/\/bit.ly\/2zdkSvB\u0022\u003Ehttp:\/\/bit.ly\/2zdkSvB\u003C\/a\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cbr \/\u003E\r\nTITLE\u003C\/p\u003E\r\n\r\n\u003Cp\u003EThe Geometry of Community Detection via the MMSE Matrix\u003C\/p\u003E\r\n\r\n\u003Cp\u003EABSTRACT\u003C\/p\u003E\r\n\r\n\u003Cdiv\u003E\r\n\u003Cp\u003EThe information-theoretic limits of community detection have been studied extensively for network models with high levels of symmetry or homogeneity. In this talk, Reeves will present a new approach that applies to a broader class of network models that allow for variability in the sizes and behaviors of the different communities, and\u0026nbsp;thus better reflect the behaviors observed in real-world networks. The results show that the ability to detect communities can be described succinctly in terms of a\u0026nbsp;matrix of effective signal-to-noise ratios that provides a geometrical representation of the relationships between the different communities. This characterization\u0026nbsp;follows from a matrix version of the I-MMSE relationship and generalizes the concept of an effective scalar signal-to-noise ratio introduced in previous work.\u0026nbsp;\u0026nbsp;\u003C\/p\u003E\r\n\u003C\/div\u003E\r\n\r\n\u003Cdiv\u003E\r\n\u003Cp\u003EThis work can be found online at\u0026nbsp;\u003Ca href=\u0022https:\/\/urldefense.proofpoint.com\/v2\/url?u=https-3A__arxiv.org_abs_1907.02496\u0026amp;d=DwMFAw\u0026amp;c=imBPVzF25OnBgGmVOlcsiEgHoG1i6YHLR0Sj_gZ4adc\u0026amp;r=rq8nYea1bgzqdyBX-JkkIxoCP0EocvNybnAaeNhmF-8\u0026amp;m=LofYkIFIH895Vhklr9OlpGld-GTD2CQLM1s9P0q1BC4\u0026amp;s=0h25GroBGlxtyhMv0n649rlQkTVWR3HuB9CiN86SuYk\u0026amp;e=\u0022\u003Ehttps:\/\/arxiv.org\/abs\/1907.02496\u003C\/a\u003E\u003C\/p\u003E\r\n\u003C\/div\u003E\r\n\r\n\u003Cp\u003EBIO\u003C\/p\u003E\r\n\r\n\u003Cp\u003EGalen Reeves joined the faculty at Duke University in Fall 2013, and is currently an Assistant Professor with a joint appointment in the\u0026nbsp;\u003Ca href=\u0022http:\/\/www.ee.duke.edu\/\u0022\u003EDepartment of Electrical \u0026amp; Computer Engineering\u0026nbsp;\u003C\/a\u003Eand the\u0026nbsp;\u003Ca href=\u0022http:\/\/stat.duke.edu\/\u0022\u003EDepartment of Statistical Science\u003C\/a\u003E. He completed his PhD in Electrical Engineering and Computer Sciences at the\u0026nbsp;\u003Ca href=\u0022http:\/\/www.eecs.berkeley.edu\/\u0022\u003EUniversity of California, Berkeley\u0026nbsp;\u003C\/a\u003Ein 2011. From 2011 to 2013 he was a postdoctoral associate in the Departments of Statistics at\u0026nbsp;\u003Ca href=\u0022http:\/\/www-stat.stanford.edu\/\u0022\u003EStanford University\u003C\/a\u003E, where he was supported by an NSF VIGRE fellowship. In the summer of 2011, he was a postdoctoral researcher in the School of Computer and Communication Sciences at\u0026nbsp;\u003Ca href=\u0022http:\/\/ic.epfl.ch\/\u0022\u003EEPFL\u003C\/a\u003E, Switzerland; in the spring of 2009, he was a visiting scholar at the\u0026nbsp;\u003Ca href=\u0022http:\/\/www.ewi.tudelft.nl\/en\u0022\u003ETechnical University of Delft\u003C\/a\u003E, The Netherlands; and in the summer of 2008, he was a research intern in the Networked Embedded Computing Group at\u0026nbsp;\u003Ca href=\u0022https:\/\/www.microsoft.com\/en-us\/research\/\u0022\u003EMicrosoft Research\u003C\/a\u003E, Redmond. He received his MS in Electrical Engineering from UC Berkeley in 2007, and BS in Electrical and Computer Engineering from\u0026nbsp;\u003Ca href=\u0022http:\/\/www.ece.cornell.edu\/\u0022\u003ECornell University\u003C\/a\u003E\u0026nbsp;in 2005.\u003C\/p\u003E\r\n","summary":null,"format":"limited_html"}],"field_subtitle":"","field_summary":"","field_summary_sentence":[{"value":"The Machine Learning Center at Georgia Tech invites you to a seminar by\u00a0Galen Reeves from Duke University."}],"uid":"34773","created_gmt":"2019-07-02 14:17:18","changed_gmt":"2019-08-26 11:07:12","author":"ablinder6","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2019-09-04T13:15:00-04:00","event_time_end":"2019-09-04T14:15:00-04:00","event_time_end_last":"2019-09-04T14:15:00-04:00","gmt_time_start":"2019-09-04 17:15:00","gmt_time_end":"2019-09-04 18:15:00","gmt_time_end_last":"2019-09-04 18:15:00","rrule":null,"timezone":"America\/New_York"},"extras":[],"hg_media":{"622936":{"id":"622936","type":"image","title":"Galen Reeves","body":null,"created":"1562078117","gmt_created":"2019-07-02 14:35:17","changed":"1562078117","gmt_changed":"2019-07-02 14:35:17","alt":"","file":{"fid":"237230","name":"gface3.jpg","image_path":"\/sites\/default\/files\/images\/gface3.jpg","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/images\/gface3.jpg","mime":"image\/jpeg","size":630631,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/images\/gface3.jpg?itok=tgHYa8bV"}}},"media_ids":["622936"],"groups":[{"id":"47223","name":"College of Computing"},{"id":"1299","name":"GVU Center"},{"id":"576481","name":"ML@GT"}],"categories":[],"keywords":[],"core_research_areas":[],"news_room_topics":[],"event_categories":[],"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":[{"value":"\u003Cp\u003EAllie McFadden\u003C\/p\u003E\r\n\r\n\u003Cp\u003ECommunications Officer\u003C\/p\u003E\r\n\r\n\u003Cp\u003Eallie.mcfadden@cc.gatech.edu\u003C\/p\u003E\r\n","format":"limited_html"}],"email":[],"slides":[],"orientation":[],"userdata":""}}}