Factorized Mutual Information Maximization
Information Theory
2019-06-14 v1 math.IT
Abstract
We investigate the sets of joint probability distributions that maximize the average multi-information over a collection of margins. These functionals serve as proxies for maximizing the multi-information of a set of variables or the mutual information of two subsets of variables, at a lower computation and estimation complexity. We describe the maximizers and their relations to the maximizers of the multi-information and the mutual information.
Keywords
Cite
@article{arxiv.1906.05460,
title = {Factorized Mutual Information Maximization},
author = {Thomas Merkh and Guido Montúfar},
journal= {arXiv preprint arXiv:1906.05460},
year = {2019}
}