
MU
Manaka Ueno, Geoffrey Wolfer
· 1 min read
ResearcharXiv cs.LG
Minimax Estimation of Discrete Distributions under Hockey-stick Divergence
arXiv:2611.19702v1 Announce Type: cross
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.
Original source
This story was published by arXiv cs.LG and written by Manaka Ueno, Geoffrey Wolfer. SyncAI.news shows a preview; the complete article is on the publisher's site.
Read the full story on arxiv.org


