Rates of convergence for robust geometric inference

F Chazal 1 P Massart 2, 3 B Michel 4
1 DATASHAPE - Understanding the Shape of Data
CRISAM - Inria Sophia Antipolis - Méditerranée , Inria Saclay - Ile de France
3 SELECT - Model selection in statistical learning
Inria Saclay - Ile de France, LMO - Laboratoire de Mathématiques d'Orsay, CNRS - Centre National de la Recherche Scientifique : UMR
Abstract : Distances to compact sets are widely used in the field of Topological Data Analysis for inferring geometric and topological features from point clouds. In this context, the distance to a probability measure (DTM) has been introduced by Chazal et al. (2011b) as a robust alternative to the distance a compact set. In practice, the DTM can be estimated by its empirical counterpart, that is the distance to the empirical measure (DTEM). In this paper we give a tight control of the deviation of the DTEM. Our analysis relies on a local analysis of empirical processes. In particular, we show that the rate of convergence of the DTEM directly depends on the regularity at zero of a particular quantile function which contains some local information about the geometry of the support. This quantile function is the relevant quantity to describe precisely how difficult is a geometric inference problem. Several numerical experiments illustrate the convergence of the DTEM and also confirm that our bounds are tight.
Type de document :
Article dans une revue
Electronic journal of statistics , Shaker Heights, OH : Institute of Mathematical Statistics, 2016, 10 (2), pp.44
Liste complète des métadonnées


https://hal.inria.fr/hal-01336913
Contributeur : Frédéric Chazal <>
Soumis le : mercredi 19 octobre 2016 - 09:55:23
Dernière modification le : jeudi 20 juillet 2017 - 09:28:16

Fichier

DTM-V3.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01336913, version 2

Citation

F Chazal, P Massart, B Michel. Rates of convergence for robust geometric inference. Electronic journal of statistics , Shaker Heights, OH : Institute of Mathematical Statistics, 2016, 10 (2), pp.44. <hal-01336913v2>

Partager

Métriques

Consultations de
la notice

194

Téléchargements du document

35