A Generalization of Independence and Multivariate Student's t-distributions

被引:2
|
作者
Sakamoto, Monta [1 ]
Matsuzoe, Hiroshi [2 ]
机构
[1] Efrei, Engn Sch Informat & Digital Technol, 30-32 Ave Republ, F-94800 Villejuif, France
[2] Nagoya Inst Technol, Dept Comp Sci & Engn, Grad Sch Engn, Showa Ku, Gokiso Cho, Nagoya, Aichi 4668555, Japan
关键词
Deformed exponential family; Deformed independence; Statistical manifold; Tsallis statistics; Information geometry; GEOMETRY;
D O I
10.1007/978-3-319-25040-3_79
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In anomalous statistical physics, deformed algebraic structures are important objects. Heavily tailed probability distributions, such as Student's t-distributions, are characterized by deformed algebras. In addition, deformed algebras cause deformations of expectations and independences of random variables. Hence, a generalization of independence for multivariate Student's t-distribution is studied in this paper. Even if two random variables which follow to univariate Student's t-distributions are independent, the joint probability distribution of these two distributions is not a bivariate Student's t-distribution. It is shown that a bivariate Student's t-distribution is obtained from two univariate Student's t-distributions under q-deformed independence.
引用
收藏
页码:740 / 749
页数:10
相关论文
共 50 条