Maximizing the Bregman divergence from a Bregman family
Information Theory
2021-11-02 v1 math.IT
Abstract
The problem to maximize the information divergence from an exponential family is generalized to the setting of Bregman divergences and suitably defined Bregman families.
Cite
@article{arxiv.2001.08813,
title = {Maximizing the Bregman divergence from a Bregman family},
author = {Johannes Rauh and František Matúš},
journal= {arXiv preprint arXiv:2001.08813},
year = {2021}
}
Comments
11 pages, 5 theorems, no figure