Normalized information-based divergences

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.
Type de document :
Article dans une revue
Problems of Information Transmission, MAIK Nauka/Interperiodica, 2007, 43 (3), pp.167-189. 〈10.1134/S0032946007030015〉
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-00022566
Contributeur : Jean-François Coeurjolly <>
Soumis le : lundi 13 novembre 2006 - 09:24:12
Dernière modification le : lundi 9 avril 2018 - 12:22:32
Document(s) archivé(s) le : lundi 20 septembre 2010 - 16:45:49

Fichiers

Identifiants

Collections

Citation

Jean-François Coeurjolly, Rémy Drouilhet, Jean-François Robineau. Normalized information-based divergences. Problems of Information Transmission, MAIK Nauka/Interperiodica, 2007, 43 (3), pp.167-189. 〈10.1134/S0032946007030015〉. 〈hal-00022566v2〉

Partager

Métriques

Consultations de la notice

281

Téléchargements de fichiers

165