Department of Computer Science Seminar
Thursday, October 17
12:45 p.m.–1:45 p.m.
Stuart Building, Room 113
Title: Differential Privacy, Adaptive Data Analysis, and Free Speedups via Sampling
Speaker: Lev Reyzin, Associate Professor of Mathematics, University of Illinois-Chicago
Abstract: In this talk, Reyzin will talk about a recently-discovered beautiful connection between differential private mechanisms and preventing overfitting in machine learning. Reyzin will discuss his work on how to use sampling to speed up such differentially-private mechanisms for machine learning without reducing the resulting accuracy. In particular, Reyzin will describe a mechanism that provides significant speed-up over previous mechanisms, without needing to increase the total amount of data required to maintain the same generalization error as before. Reyzin also will show how these general results also yield a simple, fast, and unified approach for adaptively optimizing convex and strongly convex functions over a dataset. This work is joint with Benjamin Fish and Benjamin I. P. Rubinstein.
Bio: Lev Reyzin is an Associate Professor in the MCS group at UIC’s mathematics department. His research spans the theory and practice of machine learning. Prior to joining UIC, Reyzin was a Simons Postdoctoral Fellow at Georgia Tech, and before that, an NSF CI-Fellow at Yahoo! Research, where he tackled problems in computational advertising. Reyzin received his Ph.D. on an NSF graduate research fellowship from Yale under Dana Angluin and his undergraduate degree from Princeton. His work has earned awards at ICML, COLT, and AISTATS and has been funded by the National Science Foundation and the Army Research Office.