Sup-sums principles for F-divergence, Kullback–Leibler divergence, and new definition for t-entropy

09/14/2019
by   V. I. Bakhtin, et al.
0

The article presents new sup-sums principles for integral F-divergence for arbitrary convex function F and arbitrary (not necessarily positive and absolutely continuous) measures. As applications of these results we derive the corresponding sup-sums principle for Kullback–Leibler divergence and work out new `integral' definition for t-entropy explicitly establishing its relation to Kullback–Leibler divergence.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/20/2019

Inequalities related to some types of entropies and divergences

The aim of this paper is to discuss new results concerning some kinds of...
research
06/21/2023

Quantum Rényi and f-divergences from integral representations

Smooth Csiszár f-divergences can be expressed as integrals over so-calle...
research
02/02/2021

Divergence of an integral of a process with small ball estimate

The paper contains sufficient conditions on the function f and the stoch...
research
10/01/2019

Monotonically Decreasing Sequence of Divergences

Divergences are quantities that measure discrepancy between two probabil...
research
06/14/2013

Generalized Beta Divergence

This paper generalizes beta divergence beyond its classical form associa...
research
06/10/2020

Optimal Bounds between f-Divergences and Integral Probability Metrics

The families of f-divergences (e.g. the Kullback-Leibler divergence) and...
research
04/17/2018

On f-Divergences: Integral Representations, Local Behavior, and Inequalities

This paper is focused on f-divergences, consisting of three main contrib...

Please sign up or login with your details

Forgot password? Click here to reset