Hostname: page-component-7b7567c8c-m6dxt Total loading time: 0 Render date: 2026-11-18T20:50:48.188Z Has data issue: false hasContentIssue false

Mixed ƒ-divergence for Multiple Pairs of Measures

Published online by Cambridge University Press:  20 November 2018

Elisabeth Werner
Affiliation:
Department of Mathematics, Case Western Reserve University, Cleveland, Ohio 100, USA e-mail: elisabeth.werner@case.edu
Deping Ye
Affiliation:
Department of Mathematics and Statistics, Memorial University of Newfoundland, St. John's, Newfoundland A1C SS7 e-mail: deping.ye@mun.ca
Rights & Permissions [Opens in a new window]

Abstract

Core share and HTML view are not available for this content. However, as you have access to this content, a full PDF is available via the 'Save PDF' action button.

In this paper, the concept of the classical $f$ -divergence for a pair of measures is extended to the mixed $f$ -divergence formultiple pairs ofmeasures. The mixed $f$ -divergence provides a way to measure the difference between multiple pairs of (probability) measures. Properties for the mixed $f$ -divergence are established, such as permutation invariance and symmetry in distributions. An Alexandrov–Fenchel type inequality and an isoperimetric inequality for the mixed $f$ -divergence are proved.

Information

Type
Research Article
Copyright
Copyright © Canadian Mathematical Society 2017