{"43794":{"#nid":"43794","#data":{"type":"event","title":"Model Selection\/Estimation: Multiple Reproducing Kernel Hilbert Spaces","body":[{"value":"\u003Cp\u003EIn this talk, we consider the problem of learning a target function that belongs to the linear span of a large number of reproducing Kernel Hilbert spaces. Such a problem arises naturally in many practice situations with the ANOVA, the additive model and multiple kernel learning as the most\u003Cbr \/\u003E\nwell known and important examples. We investigate approaches based on l1-type complexity regularization and the nonnegative garrote respectively. We show that the computation of both procedures can be done efficiently and the nonnegative garrote could be more favorable at times.\u003Cbr \/\u003E\nWe also study their theoretical properties from both variable selection and estimation perspective. We establish several probabilistic inequalities providing bounds on the excess risk and L2-error that depend on the sparsity of the problem. \n\u003C\/p\u003E\n\u003Cp\u003E(parts of the talk are based on joint work with Yi Lin and Vladimir Koltchinskii respectively.)\n\u003C\/p\u003E","summary":null,"format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"In this talk, we consider the problem of learning a target function that \nbelongs to the linear span of a large number of reproducing Kernel Hilbert \nspaces.,","format":"limited_html"}],"field_summary_sentence":[{"value":"Model Selection\/Estimation: Multiple Reproducing Kernel Hilbert Spaces"}],"uid":"27279","created_gmt":"2009-10-12 21:20:20","changed_gmt":"2016-10-08 01:47:54","author":"Barbara Christopher","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2008-03-25T12:05:00-04:00","event_time_end":"2008-03-25T12:55:00-04:00","event_time_end_last":"2008-03-25T12:55:00-04:00","gmt_time_start":"2008-03-25 16:05:00","gmt_time_end":"2008-03-25 16:55:00","gmt_time_end_last":"2008-03-25 16:55:00","rrule":null,"timezone":"America\/New_York"},"extras":[],"groups":[{"id":"1242","name":"School of Industrial and Systems Engineering (ISYE)"}],"categories":[],"keywords":[{"id":"5990","name":"Kernel Hilbert spaces"},{"id":"5989","name":"model selection and elimation"}],"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":"\u003Cstrong\u003EXiaoming  Huo\u003C\/strong\u003E\u003Cbr \/\u003EISyE\u003Cbr \/\u003E\u003Ca href=\u0022mailto:xiaoming.huo@isye.gatech.edu\u0022\u003EContact Xiaoming  Huo\u003C\/a\u003E\u003Cbr \/\u003E\u003Cstrong\u003E404-385-0354\u003C\/strong\u003E","format":"limited_html"}],"email":[],"slides":[],"orientation":[],"userdata":""}}}