English

Normalized information-based divergences

Statistics Theory 2016-08-16 v2 Statistics Theory

Abstract

This paper is devoted to the mathematical study of some divergences based on the mutual information well-suited to categorical random vectors. These divergences are generalizations of the "entropy distance" and "information distance". Their main characteristic is that they combine a complexity term and the mutual information. We then introduce the notion of (normalized) information-based divergence, propose several examples and discuss their mathematical properties in particular in some prediction framework.

Keywords

Cite

@article{arxiv.math/0604246,
  title  = {Normalized information-based divergences},
  author = {Jean-François Coeurjolly and Rémy Drouilhet and Jean-François Robineau},
  journal= {arXiv preprint arXiv:math/0604246},
  year   = {2016}
}

Comments

36 pages