English

Near-Optimal Bounds for Testing Histogram Distributions

Data Structures and Algorithms 2022-07-15 v1 Machine Learning Statistics Theory Statistics Theory

Abstract

We investigate the problem of testing whether a discrete probability distribution over an ordered domain is a histogram on a specified number of bins. One of the most common tools for the succinct approximation of data, kk-histograms over [n][n], are probability distributions that are piecewise constant over a set of kk intervals. The histogram testing problem is the following: Given samples from an unknown distribution p\mathbf{p} on [n][n], we want to distinguish between the cases that p\mathbf{p} is a kk-histogram versus ε\varepsilon-far from any kk-histogram, in total variation distance. Our main result is a sample near-optimal and computationally efficient algorithm for this testing problem, and a nearly-matching (within logarithmic factors) sample complexity lower bound. Specifically, we show that the histogram testing problem has sample complexity Θ~(nk/ε+k/ε2+n/ε2)\widetilde \Theta (\sqrt{nk} / \varepsilon + k / \varepsilon^2 + \sqrt{n} / \varepsilon^2).

Keywords

Cite

@article{arxiv.2207.06596,
  title  = {Near-Optimal Bounds for Testing Histogram Distributions},
  author = {Clément L. Canonne and Ilias Diakonikolas and Daniel M. Kane and Sihan Liu},
  journal= {arXiv preprint arXiv:2207.06596},
  year   = {2022}
}
R2 v1 2026-06-25T00:54:00.241Z