Minimax Boundary Estimation and Estimation with Boundary - Laboratoire de Probabilités, Statistique et Modélisation Accéder directement au contenu
Article Dans Une Revue Bernoulli Année : 2023

Minimax Boundary Estimation and Estimation with Boundary

Résumé

We derive non-asymptotic minimax bounds for the Hausdorff estimation of $d$-dimensional submanifolds $M \subset \mathbb{R}^D$ with (possibly) non-empty boundary $\partial M$. The model reunites and extends the most prevalent $\mathcal{C}^2$-type set estimation models: manifolds without boundary, and full-dimensional domains. We consider both the estimation of the manifold $M$ itself and that of its boundary $\partial M$ if non-empty. Given $n$ samples, the minimax rates are of order $O\bigl((\log n/n)^{2/d}\bigr)$ if $\partial M = \emptyset$ and $O\bigl((\log n/n)^{2/(d+1)}\bigr)$ if $\partial M \neq \emptyset$, up to logarithmic factors. In the process, we develop a Voronoi-based procedure that allows to identify enough points $O\bigl((\log n/n)^{2/(d+1)}\bigr)$-close to $\partial M$ for reconstructing it.
Fichier principal
Vignette du fichier
Minimax Boundary Estimation and Estimation with Boundary.pdf (2.42 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03317051 , version 1 (06-08-2021)
hal-03317051 , version 2 (10-03-2023)

Identifiants

Citer

Eddie Aamari, Catherine Aaron, Clément Levrard. Minimax Boundary Estimation and Estimation with Boundary. Bernoulli, 2023, ⟨10.3150/23-BEJ1585⟩. ⟨hal-03317051v2⟩
186 Consultations
105 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More