Joint Range of f-divergences

Abstract

We provide a general method for evaluation of the joint range of f-divergences for two different functions f. Via topological arguments we prove that the joint range for general distributions equals the convex hull of the joint range achieved by the distributions on a two-element set. The joint range technique provides important inequalities between different f-divergences with various applications in information theory and statistics.

arXiv commentAccepted for presentation at ISIT 2010