[4/15 (월) 세미나 안내] Rutgers University, Anand Sarwarte 교수 초청 특강: “Differential privacy can also enable scientific collaboration “
- ice
- 조회수254
- 2024-04-09
정보이론 및 신호처리 분야의 세계적인 석학이시고, IEEE IT Society의 distinguished lecturer이신 Rutgers University의 Anand Sarwarte 교수님을 모시고 다음과 같이 세미나를 개최합니다. 관심있는 많은 분들의 참여 부탁드립니다.
일시: 4월 15일(월) 오후 4시 30분
장소: 제 1공학관 21동 534호 (21534)
주제: Differential privacy can also enable scientific collaboration
(IEEE distinguished lecturer talk)
교수: Prof. Anand D. Sarwarte
Abstract
What used to be called “decentralized learning" has been rebranded as “federated learning.” In these systems, devices share summaries of locally collected data to a central aggregator, who then updates the ML model and updates the devices. With the advent of large-scale ML/AI models used in commercial technologies like mobile phones and smart home devices, it seems that all of our problems will be solved by larger and larger ML models trained on larger and larger data sets. However, many applications, such as human health research, face challenges in both sample size and privacy concerns. On paper, “local DP” can guarantee some form of differential privacy, the gold standard for measuring privacy risk.
In this talk I will explain differential privacy guarantees, how it relates to information theory and statistics, and when and how it can be made more impactful in situations such as human health research. In particular, differential privacy has can help enable the formation of research consortia. I will describe how this plays out in a collaborative research system for neuroimaging data. These application settings raise a number of interesting future research challenges.
Biography
Anand D. Sarwate is an Associate Professor in the Department of Electrical and Computer Engineering at Rutgers, the State University of New Jersey. He received a B.S. degree in Electrical Science and Engineering and a B.S. degree in Mathematics from MIT in 2002, an M.S. in Electrical Engineering from UC Berkeley in 2005 and a PhD in Electrical Engineering from UC Berkeley in 2008. From 2008-2011 he was a postdoctoral researcher at the Information Theory and Applications Center at UC San Diego and from 2011-2013 he was a Research Assistant Professor at the Toyota Technological Institute at Chicago. Prof. Sarwate was recently appointed as a Distinguished Lecturer of the IEEE Information Theory Society for 2024-2025. His interests are in information theory, machine learning, and signal processing, with applications to distributed systems, privacy and security, and biomedical research.
- 다음글
- 다음글이 없습니다.