Paperlane

no. 16 · Tuesday 17 November 2026

Minimax Estimation of Discrete Distributions under Hockey-stick Divergence

Manaka Ueno and Geoffrey Wolfer

math.ST · via stat.ML

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.

fields
Statistics Theory
pdf ↗ page arXiv:2611.19702 ↗