{"667355":{"#nid":"667355","#data":{"type":"event","title":"CSIP Seminar: Enabling Consistent Data Selection with Representation Shifts","body":[{"value":"\u003Ch3\u003E\u003Cstrong\u003ECenter for Signals and Information Processing (CSIP)\u0026nbsp;Seminar\u003C\/strong\u003E\u003C\/h3\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003EDate:\u003C\/strong\u003E\u0026nbsp;Friday, April 21,\u0026nbsp;2023\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003ETime:\u003C\/strong\u003E\u0026nbsp;3:00 p.m. - 4:00 p.m. EST\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003ELocation:\u0026nbsp;\u003C\/strong\u003ECentergy Building 5126.\u0026nbsp;The associated zoom link is:\u0026nbsp;\u003Ca href=\u0022https:\/\/gatech.zoom.us\/j\/96340868280\u0022 id=\u0022LPlnkOWALinkPreview\u0022 title=\u0022https:\/\/gatech.zoom.us\/j\/96340868280\u0022\u003Ehttps:\/\/gatech.zoom.us\/j\/96340868280\u003C\/a\u003E.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003ESpeaker:\u0026nbsp;\u003C\/strong\u003ERyan Benkert\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003ESpeakers\u0027 Title:\u003C\/strong\u003E\u0026nbsp; Ph.D. student in the Omni Lab for Intelligent Visual Engineering and Science (OLIVES) at Georgia Tech\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003ESeminar Title:\u0026nbsp;\u003C\/strong\u003EEnabling Consistent Data Selection with Representation Shifts\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003EAbstract:\u0026nbsp;\u003C\/strong\u003E\u003Cspan\u003E\u003Cspan\u003E\u003Cspan\u003E\u003Cspan\u003E\u003Cspan\u003E\u003Cspan\u003E\u003Cspan\u003ERegression describes the performance deterioration after a model update. For modern data acquisition pipelines, \u003Cspan\u003E\u003Cspan\u003Eperformance regression is a major concern as models are updated iteratively with newly acquired data. However, the current standard in several data selection paradigms assumes a direct relationship between model generalization and performance regression, namely that performance regression decreases as more training data becomes available. In this talk, I will discuss different sources of regression and demonstrate empirically that additional data can increase or decrease performance regression independently of the generalization behavior. In particular, I will explore dataset imbalance and class complexity as two influential factors in performance regression.\u003C\/span\u003E\u003C\/span\u003E \u003Cspan\u003EFurther, I will consider optimal settings where the selection algorithm has prior knowledge of the regression properties within the dataset. Based on these observations, I will derive an approximate upper bound of performance regression, giving rise to a plug-in algorithm for regression reduction in data acquisition pipelines. The talk concludes with several data acquisition experiments on in-distribution, as well as out-of-distribution, demonstrating a clear reduction with the proposed algorithm.\u003C\/span\u003E\u003C\/span\u003E\u003C\/span\u003E\u003C\/span\u003E\u003C\/span\u003E\u003C\/span\u003E\u003C\/span\u003E\u003C\/span\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003ESpeaker Bio:\u003C\/strong\u003E\u0026nbsp;\u003Cspan\u003E\u003Cspan\u003E\u003Cspan\u003E\u003Cspan\u003E\u003Cspan\u003E\u003Cspan\u003E\u003Cspan\u003E\u003Cspan\u003ERyan Benkert is a fourth-year Ph.D. student in the Omni Lab for Intelligent Visual Engineering and Science (OLIVES) at the Georgia Institute of Technology. In his research, he addresses fundamental challenges in machine learning that bridge the gap between academic research and industrial deployment. His interests include active learning, uncertainty estimation, and neural network learning dynamics. Prior to Georgia Tech, he received his B.Sc and M.Sc from the RWTH Aachen University in Germany.\u003C\/span\u003E\u003C\/span\u003E\u003C\/span\u003E\u003C\/span\u003E\u003C\/span\u003E\u003C\/span\u003E\u003C\/span\u003E\u003C\/span\u003E\u003C\/p\u003E\r\n","summary":"","format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003ERyan Benkert, a Ph.D. student in the Omni Lab for Intelligent Visual Engineering and Science (OLIVES) at Georgia Tech,\u0026nbsp;will present the April 21 CSIP Seminar, \u0022Enabling Consistent Data Selection with Representation Shifts.\u0022\u003C\/p\u003E\r\n","format":"limited_html"}],"field_summary_sentence":[{"value":"Featuring Ryan Benkert, a Ph.D. student in the Omni Lab for Intelligent Visual Engineering and Science (OLIVES) at Georgia Tech"}],"uid":"36172","created_gmt":"2023-04-14 17:05:10","changed_gmt":"2023-04-14 17:08:30","author":"dwatson71","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2023-04-21T15:00:00-04:00","event_time_end":"2023-04-21T16:00:00-04:00","event_time_end_last":"2023-04-21T16:00:00-04:00","gmt_time_start":"2023-04-21 19:00:00","gmt_time_end":"2023-04-21 20:00:00","gmt_time_end_last":"2023-04-21 20:00:00","rrule":null,"timezone":"America\/New_York"},"location":"Centergy Building 5126","extras":[],"groups":[{"id":"1255","name":"School of Electrical and Computer Engineering"}],"categories":[],"keywords":[{"id":"192224","name":"CSIP Seminar"}],"core_research_areas":[],"news_room_topics":[],"event_categories":[{"id":"1795","name":"Seminar\/Lecture\/Colloquium"}],"invited_audience":[{"id":"78761","name":"Faculty\/Staff"},{"id":"78771","name":"Public"},{"id":"78751","name":"Undergraduate students"}],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[{"value":"\u003Cp\u003EKiran Kokilepersaud\u003Cbr \/\u003E\r\n\u003Ca href=\u0022mailto:kpk6@gatech.edu\u0022\u003Ekpk6@gatech.edu\u003C\/a\u003E\u003Cbr \/\u003E\r\n\u0026nbsp;\u003C\/p\u003E\r\n","format":"limited_html"}],"email":[],"slides":[],"orientation":[],"userdata":""}}}