arxiv

Minimax Estimation of Discrete Distributions under Hockey-stick Divergence

Manaka Ueno, Geoffrey Wolfer

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.

Published
15 Nov 2026
Source
arxiv
Org
Tokyo University of Agriculture and Technology
View paper
Sign in to read and join the discussion.