Factorized Mutual Information Maximization
classification
💻 cs.IT
math.IT
keywords
informationmulti-informationmutualmaximizersvariablesaveragecollectioncomplexity
read the original 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.
This paper has not been read by Pith yet.
Forward citations
Cited by 1 Pith paper
-
The Poincar\'e-Boltzmann Machine: from Statistical Physics to Machine Learning and back
Information cohomology is computed in low degrees to establish multivariate mutual informations as k-coboundaries, with simplicial structures yielding free-energy interpretations and a topological minimum free energy complex.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.