Some inequalities relating different measures of divergence between two probability distributions

被引：4
|
作者：
Withers, L [1 ]
机构：
[1] USN, Res Lab, Washington, DC 20375 USA
来源：
IEEE TRANSACTIONS ON INFORMATION THEORY | 1999年 / 45卷 / 05期
关键词：
Bhattacharyya angle of divergence; chi-squared statistic; Cressie-Read-Anscombe statistic; directed divergence; Hellinger integrals; Kullback-Leibler cross-entropy; relative information;
D O I：
10.1109/18.771256
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
This note presents new inequalities relating different divergence measures in the family of "convex likelihood-ratio expectation" measures of Csiszar, Ali, and Silvey, and especially in the single-parameter family of "AM-GM" divergence measures. The most prominent result is that theta(2) less than or equal to 1/4J, where theta is the Bhattacharyya angle of divergence (a true distance metric), and J is the symmetric cross-entropy. A pair of "log Gamma" divergences is also introduced and related to the cross-entropies I and J.
引用
收藏
页码：1728 / 1735
页数：8
相关论文
共 50 条
12345