{"650757":{"#nid":"650757","#data":{"type":"event","title":"PhD Proposal by He Jia","body":[{"value":"\u003Cp\u003E\u003Cstrong\u003ETitle:\u0026nbsp;Robust Learning in High dimension\u003C\/strong\u003E\u003Cbr \/\u003E\r\n\u003Cbr \/\u003E\r\n\u003Cstrong\u003EDate:\u003C\/strong\u003E\u0026nbsp;Thursday, 23 September, 2021\u003Cbr \/\u003E\r\n\u003Cstrong\u003ETime:\u003C\/strong\u003E\u0026nbsp;10:00 am (EST)\u003Cbr \/\u003E\r\n\u003Cstrong\u003ELocation (Physical):\u003C\/strong\u003E\u0026nbsp;Klaus 2100 (featuring snacks)\u003Cbr \/\u003E\r\n\u003Cstrong\u003ELocation (Virtual):\u003C\/strong\u003E\u0026nbsp;\u003Ca href=\u0022https:\/\/bluejeans.com\/851759942\/0635\u0022\u003Ehttps:\/\/bluejeans.com\/851759942\/0635\u003C\/a\u003E\u0026nbsp;\u0026nbsp;\u003Cbr \/\u003E\r\n\u003Cbr \/\u003E\r\n\u003Cstrong\u003EHe Jia\u003C\/strong\u003E\u003Cbr \/\u003E\r\nPhD Student\u003Cbr \/\u003E\r\nSchool of Computer Science\u003Cbr \/\u003E\r\nGeorgia Institute of Technology\u003Cbr \/\u003E\r\n\u003Cbr \/\u003E\r\n\u003Cstrong\u003ECommittee:\u003C\/strong\u003E\u003Cbr \/\u003E\r\nSantosh Vempala (Advisor) - School of Computer Science,\u0026nbsp;Georgia Institute of Technology\u003Cbr \/\u003E\r\nKonstantin Tikhomirov - School of Mathematics,\u0026nbsp;Georgia Institute of Technology\u003Cbr \/\u003E\r\nAshwin Pananjady -\u0026nbsp;School of Industrial \u0026amp; Systems Engineering, Georgia Institute of Technology\u003Cbr \/\u003E\r\n\u003Cbr \/\u003E\r\n\u003Cstrong\u003EAbstract:\u003C\/strong\u003E\u003Cbr \/\u003E\r\nGiven a collection of observations and a class of models, the objective of a typical unsupervised learning algorithm is to find the model in the class that best fits the\u0026nbsp;data. However, real datasets are typically exposed to some source of noise. Robust statistics focuses on the design of outlier-robust estimators \u0026mdash; algorithms that can\u0026nbsp;tolerate a constant fraction of corrupted data points or other small departures from model assumptions, independent of the dimension. In the outlier-robust setting, it is\u0026nbsp;challenging to develop efficient learning algorithms for many well-known high-dimensional models.\u0026nbsp;\u003Cbr \/\u003E\r\n\u003Cbr \/\u003E\r\nWe give an efficient algorithm for the problem of robustly learning Gaussian mixtures. The main tools are an efficient\u0026nbsp;partial clustering\u0026nbsp;algorithm that relies on the\u0026nbsp;sum-of-squares method, and a novel\u0026nbsp;tensor decomposition\u0026nbsp;algorithm that allows errors in both Frobenius norm and low-rank terms. I will also discuss the problems of\u0026nbsp;robustly learning affine transformations and robustly learning multi-view models, and the possible approaches to solve these problems: e.g., robust tensor\u0026nbsp;decomposition.\u003C\/p\u003E\r\n","summary":null,"format":"limited_html"}],"field_subtitle":"","field_summary":"","field_summary_sentence":[{"value":"Robust Learning in High dimension"}],"uid":"27707","created_gmt":"2021-09-15 12:09:32","changed_gmt":"2021-09-15 12:09:32","author":"Tatianna Richardson","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2021-09-23T11:00:00-04:00","event_time_end":"2021-09-23T13:00:00-04:00","event_time_end_last":"2021-09-23T13:00:00-04:00","gmt_time_start":"2021-09-23 15:00:00","gmt_time_end":"2021-09-23 17:00:00","gmt_time_end_last":"2021-09-23 17:00:00","rrule":null,"timezone":"America\/New_York"},"extras":[],"groups":[{"id":"221981","name":"Graduate Studies"}],"categories":[],"keywords":[{"id":"102851","name":"Phd proposal"}],"core_research_areas":[],"news_room_topics":[],"event_categories":[{"id":"1788","name":"Other\/Miscellaneous"}],"invited_audience":[{"id":"78761","name":"Faculty\/Staff"},{"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":[],"email":[],"slides":[],"orientation":[],"userdata":""}}}