Replicable Distribution Testing
Preprint
Abstract
We initiate a systematic investigation of distribution testing in the framework of algorithmic replicability. Specifically, given independent samples from a collection of probability distributions, the goal is to characterize the sample complexity of replicably testing natural properties of the underlying distributions. On the algorithmic front, we develop new replicable algorithms for testing closeness and independence of discrete distributions. On the lower bound front, we develop a new methodology for proving sample complexity lower bounds for replicable testing that may be of broader interest. As an application of our technique, we establish near-optimal sample complexity lower bounds for replicable uniformity testing -- answering an open question from prior work -- and closeness testing.Keywords
All Related Versions
This publication has 4 references indexed in Scilit:
- The Bayesian Stability Zoo2023
- Nearly-Optimal Bounds for Testing Histogram Distributions2022
- An Automatic Inequality Prover and Instance Optimal Identity TestingSIAM Journal on Computing, 2017
- A Coincidence-Based Test for Uniformity Given Very Sparsely Sampled Discrete DataIEEE Transactions on Information Theory, 2008