Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
6417447 | Journal of Mathematical Analysis and Applications | 2016 | 12 Pages |
Abstract
In this paper, we present a generalization of the Kullerback-Leibler (KL) divergence in form of the Tsallis statistics. In parallel with the classical KL divergence, several important properties of this new generalization, including the pseudo-additivity, positivity and monotonicity, are shown. Moreover, some strengthened estimates on the positivity of the new divergence and the information loss during transformations are obtained.
Related Topics
Physical Sciences and Engineering
Mathematics
Analysis
Authors
Juntao Huang, Wen-An Yong, Liu Hong,