Convergence Rates for Persistence Diagram Estimation in Topological Data Analysis

Abstract : Computational topology has recently seen an important development toward data analysis, giving birth to the field of topological data analysis. Topological persistence, or persistent homology, appears as a fundamental tool in this field. In this paper, we study topological persistence in general metric spaces, with a statistical approach. We show that the use of persistent homology can be naturally considered in general statistical frameworks and that persistence diagrams can be used as statistics with interesting convergence properties. Some numerical experiments are performed in various contexts to illustrate our results.
Type de document :
Article dans une revue
Journal of Machine Learning Research, Journal of Machine Learning Research, 2015, 16, pp.3603-3635
Liste complète des métadonnées


http://hal.upmc.fr/hal-01284275
Contributeur : Gestionnaire Hal-Upmc <>
Soumis le : lundi 7 mars 2016 - 14:19:27
Dernière modification le : lundi 29 mai 2017 - 14:26:25
Document(s) archivé(s) le : dimanche 13 novembre 2016 - 08:45:03

Fichier

chazal15a.pdf
Publication financée par une institution

Licence


Distributed under a Creative Commons Paternité 4.0 International License

Identifiants

  • HAL Id : hal-01284275, version 1

Citation

Frédéric Chazal, Marc Glisse, Catherine Labruère, Bertrand Michel. Convergence Rates for Persistence Diagram Estimation in Topological Data Analysis. Journal of Machine Learning Research, Journal of Machine Learning Research, 2015, 16, pp.3603-3635. <hal-01284275>

Partager

Métriques

Consultations de
la notice

291

Téléchargements du document

85