On f-divergences Between Cauchy Distributions

被引:2
|
作者
Nielsen, Frank [1 ]
Okamura, Kazuki [2 ]
机构
[1] Sony Comp Sci Labs Inc, Tokyo, Japan
[2] Shizuoka Univ, Fac Sci, Dept Math, Shizuoka, Japan
来源
关键词
Cauchy distributions; Complex analysis; Maximal invariant; Information geometry;
D O I
10.1007/978-3-030-80209-7_86
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We prove that all f-divergences between univariate Cauchy distributions are symmetric, and can be expressed as functions of the chi-squared divergence. This property does not hold anymore for multivariate Cauchy distributions.
引用
收藏
页码:799 / 807
页数:9
相关论文
共 50 条