Generalized Pinsker Inequality for Bregman Divergences of Negative Tsallis Entropies

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Beretta, Guglielmo, Cesari, Tommaso, Colomboni, Roberto
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917251265855488
author Beretta, Guglielmo
Cesari, Tommaso
Colomboni, Roberto
author_facet Beretta, Guglielmo
Cesari, Tommaso
Colomboni, Roberto
contents The Pinsker inequality lower bounds the Kullback--Leibler divergence $D_{\textrm{KL}}$ in terms of total variation and provides a canonical way to convert $D_{\textrm{KL}}$ control into $\lVert \cdot \rVert_1$-control. Motivated by applications to probabilistic prediction with Tsallis losses and online learning, we establish a generalized Pinsker inequality for the Bregman divergences $D_α$ generated by the negative $α$-Tsallis entropies -- also known as $β$-divergences. Specifically, for any $p$, $q$ in the relative interior of the probability simplex $Δ^K$, we prove the sharp bound \[ D_α(p\Vert q) \ge \frac{C_{α,K}}{2}\cdot \|p-q\|_1^2, \] and we determine the optimal constant $C_{α,K}$ explicitly for every choice of $(α,K)$.
format Preprint
id arxiv_https___arxiv_org_abs_2602_05744
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Generalized Pinsker Inequality for Bregman Divergences of Negative Tsallis Entropies
Beretta, Guglielmo
Cesari, Tommaso
Colomboni, Roberto
Information Theory
The Pinsker inequality lower bounds the Kullback--Leibler divergence $D_{\textrm{KL}}$ in terms of total variation and provides a canonical way to convert $D_{\textrm{KL}}$ control into $\lVert \cdot \rVert_1$-control. Motivated by applications to probabilistic prediction with Tsallis losses and online learning, we establish a generalized Pinsker inequality for the Bregman divergences $D_α$ generated by the negative $α$-Tsallis entropies -- also known as $β$-divergences. Specifically, for any $p$, $q$ in the relative interior of the probability simplex $Δ^K$, we prove the sharp bound \[ D_α(p\Vert q) \ge \frac{C_{α,K}}{2}\cdot \|p-q\|_1^2, \] and we determine the optimal constant $C_{α,K}$ explicitly for every choice of $(α,K)$.
title Generalized Pinsker Inequality for Bregman Divergences of Negative Tsallis Entropies
topic Information Theory
url https://arxiv.org/abs/2602.05744