Quantcast

Joint Range of f-divergences

Research paper by Peter Harremoës, Igor Vajda

Indexed on: 27 May '10Published on: 27 May '10Published in: Computer Science - Information Theory



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.