{"625119":{"#nid":"625119","#data":{"type":"event","title":"TRIAD Lecture Series by Yuxin Chen from Princeton (3\/5)","body":[{"value":"\u003Cp\u003EThis is one of a series of talks that are given by Professor Chen. The full list of his talks is as follows:\u003Cbr \/\u003E\r\nWednesday, August 28, 2019; 11:00 am - 12:00 pm; Groseclose 402\u003Cbr \/\u003E\r\nThursday, August 29, 2019; 11:00 am - 12:00 pm; Groseclose 402\u003Cbr \/\u003E\r\nTuesday, September 3, 2019; 11:00 am - 12:00 pm; Main - Executive Education Room 228\u003Cbr \/\u003E\r\nWednesday, September 4, 2019; 11:00 am - 12:00 pm; Main - Executive Education Room 228\u003Cbr \/\u003E\r\nThursday, September 5, 2019; 11:00 am - 12:00 pm; Groseclose 402\u003C\/p\u003E\r\n\r\n\u003Cp\u003ECheck https:\/\/triad.gatech.edu\/events for more information.\u0026nbsp;\u003Cbr \/\u003E\r\nFor location information, please check https:\/\/isye.gatech.edu\/about\/maps-directions\/isye-building-complex\u003C\/p\u003E\r\n\r\n\u003Cp\u003ETitle of this talk: The projected power method: an efficient nonconvex algorithm for a joint discrete assignment from\u0026nbsp;pairwise data\u003C\/p\u003E\r\n\r\n\u003Cp\u003EAbstract: Various applications involve assigning discrete label values to a collection of objects based on some\u0026nbsp;pairwise noisy data. Due to the discrete---and hence nonconvex---structure of the problem, computing the\u0026nbsp;optimal assignment (e.g. maximum likelihood assignment) becomes intractable at first sight.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EThis paper makes progress towards efficient computation by focusing on a concrete joint discrete alignment\u0026nbsp;problem---that is, the problem of recovering n discrete variables given noisy observations of their modulo\u0026nbsp;differences. We propose a low-complexity and model-free procedure, which operates in a lifted space by\u0026nbsp;representing distinct label values in orthogonal directions, and which attempts to optimize quadratic functions\u0026nbsp;over hypercubes. Starting with a first guess computed via a spectral method, the algorithm successively refines\u0026nbsp;the iterates via projected power iterations. We prove that for a broad class of statistical models, the\u0026nbsp;proposed projected power method makes no error---and hence converges to the maximum likelihood estimate---in a suitable regime. Numerical experiments have been carried out on both synthetic and real data to demonstrate the\u003Cbr \/\u003E\r\npracticality of our algorithm. We expect this algorithmic framework to be effective for a broad range of\u0026nbsp;discrete assignment problems.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EThis is joint work with Emmanuel Candes.\u003C\/p\u003E\r\n","summary":null,"format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003EThis is one of a series of talks that are given by Professor Chen. The full list of his talks is as follows:\u003Cbr \/\u003E\r\nWednesday, August 28, 2019; 11:00 am - 12:00 pm; Groseclose 402\u003Cbr \/\u003E\r\nThursday, August 29, 2019; 11:00 am - 12:00 pm; Groseclose 402\u003Cbr \/\u003E\r\nTuesday, September 3, 2019; 11:00 am - 12:00 pm; Main - Executive Education Room 228\u003Cbr \/\u003E\r\nWednesday, September 4, 2019; 11:00 am - 12:00 pm; Main - Executive Education Room 228\u003Cbr \/\u003E\r\nThursday, September 5, 2019; 11:00 am - 12:00 pm; Groseclose 402\u003C\/p\u003E\r\n\r\n\u003Cp\u003ECheck https:\/\/triad.gatech.edu\/events for more information.\u0026nbsp;\u003Cbr \/\u003E\r\nFor location information, please check https:\/\/isye.gatech.edu\/about\/maps-directions\/isye-building-complex\u003Cbr \/\u003E\r\n\u0026nbsp;\u003C\/p\u003E\r\n","format":"limited_html"}],"field_summary_sentence":[{"value":"This is one of a series of talks that are given by Professor Chen."}],"uid":"34963","created_gmt":"2019-08-25 17:29:11","changed_gmt":"2019-09-03 20:06:21","author":"Xiaoming Huo","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2019-09-03T12:00:00-04:00","event_time_end":"2019-09-03T13:00:00-04:00","event_time_end_last":"2019-09-03T13:00:00-04:00","gmt_time_start":"2019-09-03 16:00:00","gmt_time_end":"2019-09-03 17:00:00","gmt_time_end_last":"2019-09-03 17:00:00","rrule":null,"timezone":"America\/New_York"},"extras":[],"related_links":[{"url":"http:\/\/www.princeton.edu\/~yc5\/slides\/Alignment_slides_long.pdf","title":"Talk Slides at Speaker\u0027s web site"}],"groups":[{"id":"602673","name":"TRIAD "}],"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"}],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[],"email":[],"slides":[],"orientation":[],"userdata":""}}}