{"71531":{"#nid":"71531","#data":{"type":"event","title":"Statistics seminar - Nonparametric Graph Estimation","body":[{"value":"\u003Cp\u003ETITLE: Nonparametric Graph Estimation\u003C\/p\u003E\u003Cp\u003ESPEAKER: Han Liu, Johns Hopkins University\u003C\/p\u003E\u003Cp\u003EABSTRACT:\u003C\/p\u003E\u003Cp\u003EGraphical models have proven to\n      be an extremely useful abstraction in statistical machine learning. The starting point is the graph of a distribution. While usually the graph is assumed given, we are interested in estimating the graph from data. In this talk we\n      present\u003Cbr \/\u003E\n      several new nonparametric and semiparametric methods for graph estimation. One approach is named \u0022the nonparanormal,\u0022 which uses copula methods to transform the variables by monotonic functions, relaxing the fully parametric assumptions made by the Gaussian\u003Cbr \/\u003E\n      graphical model. Another approach is to restrict the family of\n      allowed graphs to forest graphs, enabling the use of fully nonparametric density estimation. Finally, we introduce a new framework named \u0022graph-valued regression\u0022 where the graph is estimated conditioned\n      on\u003Cbr \/\u003E\n      a recursive partition of a set of covariates. The resulting\n      methods are easy to understand and compute, theoretically well supported,\n      and effective for modeling and exploring high dimensional data. Joint\n      work with Fang Han, John Lafferty, Larry Wasserman, and Tuo Zhao.\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EBio: \u003C\/strong\u003EHan\n      Liu graduated from the joint Ph.D. program in Machine Learning and Statistics at Carnegie Mellon University in 2011.\n      \u0026nbsp;Since then he became an assistant professor of Biostatistics and\n      Computer Science at Johns Hopkins University. His research lies at the intersection of Modern Statistics and\n      Computer Science. Especially, he is interested in large-scale nonparametric methods, which directly conduct inference in infinite-dimensional\u003Cbr \/\u003E\n      spaces and are more flexible to capture the subtleties in modern applications. He is the PI of a NSF grant and has won several\n      academic awards, including the J. Tinsley Oden faculty fellowship from UT Austin, the best overall paper runner up award at the 26th\u003Cbr \/\u003E\n      international conference of Machine Learning and a PHD fellowship\n      from Google.\u003C\/p\u003E","summary":null,"format":"limited_html"}],"field_subtitle":"","field_summary":"","field_summary_sentence":[{"value":"Nonparametric Graph Estimation"}],"uid":"27187","created_gmt":"2011-10-18 13:46:33","changed_gmt":"2016-10-08 01:56:24","author":"Anita Race","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2011-10-26T12:00:00-04:00","event_time_end":"2011-10-26T13:00:00-04:00","event_time_end_last":"2011-10-26T13:00:00-04:00","gmt_time_start":"2011-10-26 16:00:00","gmt_time_end":"2011-10-26 17:00:00","gmt_time_end_last":"2011-10-26 17:00:00","rrule":null,"timezone":"America\/New_York"},"extras":[],"groups":[{"id":"1242","name":"School of Industrial and Systems Engineering (ISYE)"}],"categories":[],"keywords":[{"id":"166896","name":"seminar"},{"id":"167169","name":"statistics"}],"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":"\u003Cp\u003EKwok Tsui\u003C\/p\u003E","format":"limited_html"}],"email":[],"slides":[],"orientation":[],"userdata":""}}}