stat.MLNov 15, 2026

Minimax Estimation of Discrete Distributions under Hockey-stick Divergence

Authors: Manaka Ueno, Geoffrey Wolfer

Organizations: Department of Electrical Engineering and Computer Science, Tokyo University of Agriculture and Technology, Tokyo

Abstract

We initiate the study of estimating a discrete distribution with respect to the hockey-stick divergence from independent samples. We provide non-asymptotic upper and lower bounds on the minimax expected loss in terms of the alphabet size, the number of samples, and the divergence parameter. The upper bounds are achieved by add-constant estimators, while the lower bound is derived via a Bayes risk argument. Both upper bounds and lower bounds reveal a transition between polynomial and exponential regimes as the parameters of the problem vary.

Explore similar work

May 28, 2026

Improved Distribution Estimation in ℓ∞\ell_\infty

We present improved bounds for estimating discrete probability distributions under the ℓ∞\ell_\infty norm. These include minimax bounds in expectation and high-probability tail bounds. We resolve some of the open questions posed in Kontorovich and Painsky (JMLR, 2025) -- including a fully empirical version of the tightest risk bound they presented and identifying the form of the worst-case extremal distribution. Encouraging empirical results are reported as well.
Jul 27, 2026

Minimax Lower Bounds of Kernel Discrepancy Estimation: MMD, HSIC, KSD

Over the past 20 years, kernel discrepancies have been leveraged as a highly powerful tool for quantifying the disagreement of distributions, with numerous successful applications in two-sample, goodness-of-fit, and independence testing, among others. Their fastest estimators are known to converge at a parametric rate---n−1/2n^{-1/2}---under mild conditions. While this rate is known to be minimax optimal on Rd\mathbb R^d under strict assumptions with bounded kernels, little is known about its optimality beyond the finite-dimensional Euclidean setting with unbounded kernels. In this work, we prove that the minimax lower bound of estimation of the most popular kernel discrepancies (maximum mean discrepancy, Hilbert-Schmidt independence criterion and kernel Stein discrepancy; MMD, HSIC, KSD) is n−1/2n^{-1/2} on general topological spaces, and under mild assumptions on the kernel; the same rates are shown (as corollaries) to hold for the estimation of the mean embedding and the centered cross-covariance operator. Our results settle the question of optimal estimation of these kernel discrepancies.
Mar 12, 2026

Simultaneous estimation of multiple discrete unimodal distributions under stochastic order constraints

We study the problem of estimating multiple discrete unimodal distributions, motivated by search behavior analysis on a real-world platform. To incorporate prior knowledge of precedence relations among distributions, we impose stochastic order constraints and formulate the estimation task as a mixed-integer convex quadratic optimization problem. Experiments on both synthetic and real datasets show that the proposed method reduces the Jensen-Shannon divergence by 2.2% on average (up to 6.3%) when the sample size is small, while performing comparably to existing methods when sufficient data are available.