A weighted k-nearest neighbor density estimate for geometric inference

Gérard Biau 1, 2, 3 Frédéric Chazal 4 David Cohen-Steiner 4 Luc Devroye 5 Carlos Rodríguez 6
1 LPMA - Laboratoire de Probabilités et Modèles Aléatoires
2 LSTA - Laboratoire de Statistique Théorique et Appliquée
3 DMA - Département de Mathématiques et Applications
4 GEOMETRICA - Geometric computing
CRISAM - Inria Sophia Antipolis - Méditerranée , Inria Saclay - Ile de France
5 SOCS - School of Computer Science [Quebec]
6 University at Albany
Abstract : Motivated by a broad range of potential applications in topological and geometric inference, we introduce a weighted version of the k-nearest neighbor density estimate. Various pointwise consistency results of this estimate are established. We present a general central limit theorem under the lightest possible conditions. In addition, a strong approximation result is obtained and the choice of the optimal set of weights is discussed. In particular, the classical k-nearest neighbor estimate is not optimal in a sense described in the manuscript. The proposed method has been implemented to recover level sets in both simulated and real-life data.
Keywords : geometric inference density estimation
Type de document :
Article dans une revue
Electronic journal of statistics , Shaker Heights, OH : Institute of Mathematical Statistics, 2011, 5, pp.204-237. <http://projecteuclid.org/euclid.ejs/1302784854>
Liste complète des métadonnées
https://hal.inria.fr/hal-01094871
Contributeur : Frédéric Chazal <>
Soumis le : dimanche 14 décembre 2014 - 11:33:16
Dernière modification le : jeudi 27 avril 2017 - 09:46:33

Identifiants

  • HAL Id : hal-01094871, version 1

Collections

UPMC | INRIA | LSTA | PSL | USPC | PMA

Citation

Gérard Biau, Frédéric Chazal, David Cohen-Steiner, Luc Devroye, Carlos Rodríguez. A weighted k-nearest neighbor density estimate for geometric inference. Electronic journal of statistics , Shaker Heights, OH : Institute of Mathematical Statistics, 2011, 5, pp.204-237. <http://projecteuclid.org/euclid.ejs/1302784854>. <hal-01094871>

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

302

Contact


archive-ouverte@inria.fr