Time：2019/6/7 16:00-17:00

Location：Mingde Main Building 1016

Topic：Gaussian Differential Privacy

Abstract:

Differential privacy has seen remarkable success as a rigorous and practical formalization of data privacy in the past decade. This privacy definition and its divergence based relaxations, however, have several acknowledged weaknesses, either in handling composition of private algorithms or in analyzing important primitives like privacy amplification by subsampling. Inspired by the hypothesis testing formulation of privacy, this talk proposes a new relaxation, which we term `f-differential privacy` (f-DP). This notion of privacy has a number of appealing properties and, in particular, avoids difficulties associated with divergence based relaxations. First, f-DP preserves the hypothesis testing interpretation. In addition, f-DP allows for lossless reasoning about composition in an algebraic fashion. Moreover, we provide a powerful technique to import existing results proven for original DP to f-DP and, as an application, obtain a simple subsampling theorem for f-DP.

In addition to the above findings, we introduce a canonical single-parameter family of privacy notions within the f-DP class that is referred to as `Gaussian differential privacy` (GDP), defined based on testing two shifted Gaussians. GDP is focal among the f-DP class because of a central limit theorem we prove. More precisely, the privacy guarantees of emph{any} hypothesis testing based definition of privacy (including original DP) converges to GDP in the limit under composition. The CLT also yields a computationally inexpensive tool for analyzing the exact composition of private algorithms. Taken together, this collection of attractive properties render f-DP a mathematically coherent, analytically tractable, and versatile framework for private data analysis. Finally, we demonstrate the use of the tools we develop by giving an improved privacy analysis of noisy stochastic gradient descent.

Resume：

Weijie Su is an Assistant Professor of Statistics at the Wharton School, University of Pennsylvania. Prior to joining Penn, he received his Ph.D. in Statistics from Stanford University in 2016 and his B.S. in Mathematics from Peking University in 2011. His research interests span statistical machine learning,  private data analysis, optimization, high-dimensional statistics, and multiple hypothesis testing. He is a recipient of the NSF CAREER Award in 2019.