A CLASS OF RENYI INFORMATION ESTIMATORS FOR MULTIDIMENSIONAL DENSITIES

Abstract : A class of estimators of the Rényi and Tsallis entropies of an unknown distribution f in R^m is presented. These estimators are based on the k-th nearest-neighbor distances computed from a sample of N i.i.d. vectors with distribution f. We show that entropies of any order q, including Shannon's entropy, can be estimated consistently with minimal assumptions on f. Moreover, we show that it is straightforward to extend the nearest-neighbor method to estimate the statistical distance between two distributions using one i.i.d. sample from each.
Type de document :
Article dans une revue
The Annals of Statistics, IMS, 2008, 36 (5), pp.2153-2182. <10.1214/07-AOS539>
Liste complète des métadonnées


https://hal.archives-ouvertes.fr/hal-00331300
Contributeur : Luc Pronzato <>
Soumis le : jeudi 16 octobre 2008 - 11:21:26
Dernière modification le : mercredi 8 décembre 2010 - 18:07:47
Document(s) archivé(s) le : lundi 7 juin 2010 - 18:11:32

Fichier

AOS539.pdf
Fichiers éditeurs autorisés sur une archive ouverte

Identifiants

Collections

Citation

Nikolai Leonenko, Luc Pronzato, Vippal Savani. A CLASS OF RENYI INFORMATION ESTIMATORS FOR MULTIDIMENSIONAL DENSITIES. The Annals of Statistics, IMS, 2008, 36 (5), pp.2153-2182. <10.1214/07-AOS539>. <hal-00331300>

Partager

Métriques

Consultations de
la notice

161

Téléchargements du document

93