Differentially Private Testing of Identity and Closeness of Discrete Distributions

TL;DR

This paper establishes optimal sample complexity bounds for differentially private identity and closeness testing of discrete distributions, introducing new algorithms and a general framework for lower bounds.

Contribution

It provides the first optimal algorithms for private closeness testing and a novel framework for lower bounds in private statistical testing.

Findings

Optimal sample complexity algorithms for identity testing.

First results and optimal bounds for private closeness testing.

A general framework for lower bounds using coupling and priors.

Abstract

We study the fundamental problems of identity testing (goodness of fit), and closeness testing (two sample test) of distributions over $k$ elements, under differential privacy. While the problems have a long history in statistics, finite sample bounds for these problems have only been established recently. In this work, we derive upper and lower bounds on the sample complexity of both the problems under $(\varepsilon, \delta)$-differential privacy. We provide optimal sample complexity algorithms for identity testing problem for all parameter ranges, and the first results for closeness testing. Our closeness testing bounds are optimal in the sparse regime where the number of samples is at most $k$. Our upper bounds are obtained by privatizing non-private estimators for these problems. The non-private estimators are chosen to have small sensitivity. We propose a general framework to establish lower bounds on the sample complexity of statistical tasks under differential privacy. We show a bound on differentially private algorithms in terms of a coupling between the two hypothesis classes we aim to test. By constructing carefully chosen priors over the hypothesis classes, and using Le Cam's two point theorem we provide a general mechanism for proving lower bounds. We believe that the framework can be used to obtain strong lower bounds for other statistical tasks under privacy.