CoinPress: Practical Private Mean and Covariance Estimation

A Google TechTalk, presented by Guatam Kamal, 2021/03/05 ABSTRACT: Differential Privacy for ML Series. We introduce a simple framework for differentially private estimation. As a case study, we will focus on mean estimation for sub-Gaussian data. In this setting, our algorithm is highly effective both theoretically and practically, matching state-of-the-art theoretical bounds, and concretely outperforming all previous methods. Specifically, previous estimators either have weak empirical accuracy at small sample sizes, perform poorly for multivariate data, or require the user to provide strong a priori estimates for the parameters. Based on joint work with Sourav Biswas, Yihe Dong, and Jonathan Ullman. About the speaker: Gautam Kamath is an Assistant Professor at the University of Waterloo’s Cheriton School of Computer Science, and a faculty affiliate at the Vector Institute. He is interested in principled methods for statistics and machine learning, with a focus on settings which are common in modern data analysis (primarily privacy and robustness). He was a Microsoft Research Fellow at the Simons Institute for the Theory of Computing for the Fall 2018 semester program on Foundations of Data Science and the Spring 2019 semester program on Data Privacy: Foundations and Applications. Before that, he completed his Ph.D. at MIT, affiliated with the Theory of Computing group in CSAIL.