Minimax adaptive estimation in manifold inference - Inria - Institut national de recherche en sciences et technologies du numérique
Journal Articles Electronic Journal of Statistics Year : 2021

Minimax adaptive estimation in manifold inference

Estimation minimax adaptative en inférence géométrique

Abstract

We focus on the problem of manifold estimation: given a set of observations sampled close to some unknown submanifold M , one wants to recover information about the geometry of M . Minimax estimators which have been proposed so far all depend crucially on the a priori knowledge of parameters quantifying the underlying distribution generating the sample (such as bounds on its density), whereas those quantities will be unknown in practice. Our contribution to the matter is twofold. First, we introduce a one-parameter family of manifold estimators (M t) t≥0 based on a localized version of convex hulls, and show that for some choice of t, the corresponding estimator is minimax on the class of models of C 2 manifolds introduced in [Genovese et al., Manifold estimation and singular deconvolution under Hausdorff loss]. Second, we propose a completely data-driven selection procedure for the parameter t, leading to a minimax adaptive manifold estimator on this class of models. This selection procedure actually allows us to recover the Hausdorff distance between the set of observations and M , and can therefore be used as a scale parameter in other settings, such as tangent space estimation.
Fichier principal
Vignette du fichier
divol.pdf (1.2 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-02440881 , version 1 (15-01-2020)
hal-02440881 , version 2 (08-06-2020)
hal-02440881 , version 3 (26-10-2021)

Identifiers

Cite

Vincent Divol. Minimax adaptive estimation in manifold inference. Electronic Journal of Statistics , 2021, ⟨10.1214/21-EJS1934⟩. ⟨hal-02440881v3⟩
147 View
180 Download

Altmetric

Share

More