Communications in Mathematical Sciences

Volume 6 (2008)

Number 4

Metrics defined by Bregman divergences: Part 2

Pages: 927 – 948

DOI: http://dx.doi.org/10.4310/CMS.2008.v6.n4.a7

Authors

P. Chen

Y. Chen

M. Rao

Abstract

Bregman divergences have played an important role in many research areas. Divergence is a measure of dissimilarity and by itself is not a metric. If a function of the divergence is a metric, then it becomes much more powerful. In Part 1 we have given necessary and sufficient conditions on the convex function in order that the square root of the averaged associated divergence is a metric. In this paper we provide a min-max approach to getting a metric from Bregman divergence. We show that the "capacity" to the power 1/e is a metric.

Keywords

Metrics; Bregman divergence; triangle inequality; Kullback-Leibler divergence; Shannon entropy; capacity

2010 Mathematics Subject Classification

26D10, 94A15

Full Text (PDF format)