Persistence Diagram Estimation : Beyond Plug-in Approaches - Archive ouverte HAL
Pré-Publication, Document De Travail Année : 2024

Persistence Diagram Estimation : Beyond Plug-in Approaches

Résumé

Persistent homology is a tool from Topological Data Analysis (TDA) used to summarize the topology underlying data. It can be conveniently represented through persistence diagrams. Observing a noisy signal, common strategies to infer its persistence diagram involve plug-in estimators, and convergence properties are then derived from sup-norm stability. This dependence on the sup-norm convergence of the preliminary estimator is restrictive, as it essentially imposes to consider regular classes of signals. Departing from these approaches, we design an estimator based on image persistence. In the context of the Gaussian white noise model, and for large classes of piecewise-Hölder signals, we prove that the proposed estimator is consistent and achieves minimax rates. Notably, these rates coincide with the well known minimax rates for Hölder continuous signals.
Fichier principal
Vignette du fichier
Article_Mu_reach_V15 (1).pdf (946.13 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04593678 , version 1 (30-05-2024)
hal-04593678 , version 2 (22-07-2024)
hal-04593678 , version 3 (27-08-2024)

Licence

Identifiants

  • HAL Id : hal-04593678 , version 2

Citer

Hugo Henneuse. Persistence Diagram Estimation : Beyond Plug-in Approaches. 2024. ⟨hal-04593678v2⟩
71 Consultations
35 Téléchargements

Partager

More