AI4OPT Seminar Series
Date: Thursday, February 2, 2023
Time: Noon – 1:00 pm
Location: Instructional Center 115 (Scale Up Room) - (759 Ferst Dr, Atlanta, GA 30318)
Join Virtually: https://gatech.zoom.us/j/99381428980
Speaker: Gautam Kamath
Efficient Private Mean Estimation
Abstract: We give the first polynomial-time algorithm to estimate the mean of a d-dimensional probability distribution with bounded covariance from Õ(d) independent samples subject to pure differential privacy. Prior algorithms for this problem either incur exponential running time, require Ω(d1.5) samples, or satisfy only the weaker approximate differential privacy condition. Some interesting connections with robust statistics are uncovered along the way. No familiarity with differential privacy or robust statistics is assumed.
Based on work in STOC 2022 with Samuel B. Hopkins and Mahbod Majid. ArXiv preprint available at https://arxiv.org/abs/2111.12981
Bio: Gautam Kamath is an assistant professor at the David R. Cheriton School of Computer Science at the University of Waterloo, and a faculty affiliate at the Vector Institute. He has a B.S. in Computer Science and Electrical and Computer Engineering from Cornell University, and an M.S. and Ph.D. in Computer Science from the Massachusetts Institute of Technology. Kamath is interested in reliable and trustworthy statistics and machine learning, including considerations such as data privacy and robustness. He was a Microsoft Research Fellow, as part of the Simons-Berkeley Research Fellowship Program at the Simons Institute for the Theory of Computing. Kamath is a recipient of the NSERC Discovery Accelerator Supplement program and was awarded the Best Student Presentation Award at the ACM Symposium on Theory of Computing.
Lunch will be served at the seminar. So, please stop by 15 minutes before the seminar to pick up lunch.
To receive AI4OPT seminar announcements, please sign up to our mailing list. at https://lists.isye.gatech.edu/mailman/listinfo/ai4opt-seminars.
Past seminars can be found at https://www.ai4opt.org/seminars/past-seminars.