Knauf A, Ay N (2006)
Publication Type: Journal article, Original article
Publication year: 2006
Publisher: Institute of Information Theory and Automation of the ASCR
Book Volume: 42
Pages Range: 517--538
Journal Issue: 5
Stochastic interdependence of a probability distribution on a product space is measured by its Kullback–Leibler distance from the exponential family of product distributions (called multi-information). Here we investigate low-dimensional exponential families that contain the maximizers of stochastic interdependence in their closure. Based on a detailed description of the structure of probability distributions with globally maximal multi-information we obtain our main result: The exponential family of pure pair-interactions contains all global maximizers of the multi-information in its closure.
APA:
Knauf, A., & Ay, N. (2006). Maximizing Multi-information. Kybernetika, 42(5), 517--538.
MLA:
Knauf, Andreas, and Nihat Ay. "Maximizing Multi-information." Kybernetika 42.5 (2006): 517--538.
BibTeX: Download