Normalized information-based divergences

Research paper by Jean-François Coeurjolly, Rémy Drouilhet, Jean-François Robineau

Indexed on: 13 Nov '06Published on: 13 Nov '06Published in: Mathematics - Statistics


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.