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.
Keywords: multi-information; exponential family; relative entropy; pair-interaction; infomax principle; Boltzmann machine; neural networks;
AMS: 82C32; 92B20; 94A15;
BACK to VOLUME 42 NO.5