On Scalable Testing of Samplers Download PDF

Published: 31 Oct 2022, Last Modified: 15 Jan 2023NeurIPS 2022 AcceptReaders: Everyone
Keywords: Sampling, Distribution Testing, Constraints
Abstract: In this paper we study the problem of testing of constrained samplers over high-dimensional distributions with $(\varepsilon,\eta,\delta)$ guarantees. Samplers are increasingly used in a wide range of safety-critical ML applications, and hence the testing problem has gained importance. For $n$-dimensional distributions, the existing state-of-the-art algorithm, $\mathsf{Barbarik2}$, has a worst case query complexity of exponential in $n$ and hence is not ideal for use in practice. Our primary contribution is an exponentially faster algorithm, $\mathsf{Barbarik3}$, that has a query complexity linear in $n$ and hence can easily scale to larger instances. We demonstrate our claim by implementing our algorithm and then comparing it against $\mathsf{Barbarik2}$. Our experiments on the samplers $\mathsf{wUnigen3}$ and $\mathsf{wSTS}$, find that $\mathsf{Barbarik3}$ requires $10\times$ fewer samples for $\mathsf{wUnigen3}$ and $450\times$ fewer samples for $\mathsf{wSTS}$ as compared to $\mathsf{Barbarik2}$.
TL;DR: Constrained samplers generate samples from hard distributions. We present a tool that can test whether your sampler does actually generate samples from the right distribution.
Supplementary Material: zip
11 Replies