{"640750":{"#nid":"640750","#data":{"type":"event","title":"PhD Proposal by David Byrd","body":[{"value":"\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003ETitle:\u003C\/strong\u003E\u0026nbsp;Ethically constrained and privacy preserving learning in agent-based simulation\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003EDavid Byrd\u003C\/p\u003E\r\n\r\n\u003Cp\u003EPh.D. Student\u003C\/p\u003E\r\n\r\n\u003Cp\u003ESchool of Interactive Computing\u003C\/p\u003E\r\n\r\n\u003Cp\u003EGeorgia Institute of Technology\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003EDate:\u003C\/strong\u003E Thursday, November 5th, 2020\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003ETime: \u003C\/strong\u003E3:00 pm to 5:00 pm (EST)\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003ELocation: *No Physical Location*\u003C\/strong\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003EBlueJeans: \u003C\/strong\u003E\u003Ca href=\u0022https:\/\/bluejeans.com\/5512415242\u0022\u003Ehttps:\/\/bluejeans.com\/5512415242\u003C\/a\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003ECommittee:\u003C\/strong\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003EDr. Tucker Balch (advisor), School of Interactive Computing, Georgia Institute of Technology\u003C\/p\u003E\r\n\r\n\u003Cp\u003EDr. Mark Riedl, School of Interactive Computing, Georgia Institute of Technology\u003C\/p\u003E\r\n\r\n\u003Cp\u003EDr. Thad Starner, School of Interactive Computing, Georgia Institute of Technology\u003C\/p\u003E\r\n\r\n\u003Cp\u003EDr. Maria Hybinette, Deptartment of Computer Science, University of Georgia\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Cstrong\u003EAbstract:\u003C\/strong\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003EThis dissertation aims to advance responsible machine learning in two important areas, ethically-constrained learning and privacy-preserving federated learning, through the application of agent-based simulation.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003EAs machine learning (ML) models increase in complexity and capacity, there is a concomitant increase in the risk that ML-based agents may adopt unintended harmful behaviors during training.\u0026nbsp; For example, a trading algorithm with a flexible action space, optimizing for maximum profit, may inadvertently discover an unlawful approach that relies on market manipulation.\u0026nbsp; Complex models can also require vast user-collected training data sets and distributed learning techniques that increase the risk of exposing sensitive personal information.\u0026nbsp; Agent-based simulation (ABS) enables a safe and cost-effective approach to the investigation of these two important problems.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003EThe first problem addressed is ethically-constrained learning, to which we propose a generic solution and demonstrate it by application to financial markets.\u0026nbsp; We construct a realistic simulation of profit-driven but ethical\u0026nbsp; agents trading through a stock exchange, introduce an unethical agent, and learn to recognize the unethical behavior.\u0026nbsp; Then we use the recognizer to train an intelligent trading agent that will generate profit while avoiding policies that approach the unethical behavior pattern.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003EThe second problem addressed is privacy-preserving federated learning (PPFL).\u0026nbsp; We implement two PPFL protocols in simulation: a recent state of the art protocol using differential privacy and secure multiparty computation with homomorphic encryption and a new protocol incorporating oblivious distributed differential privacy.\u0026nbsp; The simulation permits us to inexpensively evaluate both protocols for model accuracy, computational complexity, communication load, and resistance to collusion attacks by participating parties.\u0026nbsp; We demonstrate that the new protocol increases computation and communication costs, but substantially improves privacy with no loss of accuracy to the final shared model.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026nbsp;\u003C\/p\u003E\r\n","summary":null,"format":"limited_html"}],"field_subtitle":"","field_summary":"","field_summary_sentence":[{"value":"Ethically constrained and privacy preserving learning in agent-based simulation"}],"uid":"27707","created_gmt":"2020-10-29 15:22:12","changed_gmt":"2020-10-29 15:22:12","author":"Tatianna Richardson","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2020-11-05T15:00:00-05:00","event_time_end":"2020-11-05T17:00:00-05:00","event_time_end_last":"2020-11-05T17:00:00-05:00","gmt_time_start":"2020-11-05 20:00:00","gmt_time_end":"2020-11-05 22:00:00","gmt_time_end_last":"2020-11-05 22:00:00","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":""}}}