Testing probability distributions using conditional samples

TL;DR

This paper introduces a flexible conditional sampling framework for testing properties of probability distributions, enabling significantly more efficient algorithms with query complexities that are polylogarithmic in the domain size, contrasting with traditional methods.

Contribution

It develops a new conditional sampling model for distribution testing and provides both upper and lower bounds, demonstrating its power over standard models.

Findings

Polylogarithmic query algorithms for uniformity testing

Efficient algorithms for distribution identity testing

Lower bounds matching the new model's capabilities

Abstract

We study a new framework for property testing of probability distributions, by considering distribution testing algorithms that have access to a conditional sampling oracle.* This is an oracle that takes as input a subset $S \subseteq [N]$ of the domain $[N]$ of the unknown probability distribution $D$ and returns a draw from the conditional probability distribution $D$ restricted to $S$. This new model allows considerable flexibility in the design of distribution testing algorithms; in particular, testing algorithms in this model can be adaptive. We study a wide range of natural distribution testing problems in this new framework and some of its variants, giving both upper and lower bounds on query complexity. These problems include testing whether $D$ is the uniform distribution $\mathcal{U}$; testing whether $D = D^\ast$ for an explicitly provided $D^\ast$; testing whether two unknown distributions $D_1$ and $D_2$ are equivalent; and estimating the variation distance between $D$ and the uniform distribution. At a high level our main finding is that the new "conditional sampling" framework we consider is a powerful one: while all the problems mentioned above have $\Omega(\sqrt{N})$ sample complexity in the standard model (and in some cases the complexity must be almost linear in $N$), we give $\mathrm{poly}(\log N, 1/\varepsilon)$-query algorithms (and in some cases $\mathrm{poly}(1/\varepsilon)$-query algorithms independent of $N$) for all these problems in our conditional sampling setting. *Independently from our work, Chakraborty et al. also considered this framework. We discuss their work in Subsection [1.4].