Maximizing Multi-Information

Nihat Ay and Andreas Knauf

Contact the author: Please use for correspondence this email.
Submission date: 30. Apr. 2003
Pages: 31
published in: Kybernetika, 42 (2006) 5, p. 517-538 
Bibtex
Keywords and phrases: multi-information, pair-interaction, infomax principle
Download full preprint: PDF (307 kB), PS ziped (352 kB)

Abstract:
We investigate the structure of the global maximizers of stochastic interdependence, which is measured by the Kullback-Leibler divergence of the underlying joint probability distribution from the exponential family of factorizable random fields (multi-information). As a consequence of our structure results, it comes out that random fields with globally maximal multi-information are contained in the topological closure of the exponential family of pair interactions.