Non-Asymptotic Rates for Manifold, Tangent Space, and Curvature Estimation - Archive ouverte HAL
Journal Articles Annals of Statistics Year : 2019

Non-Asymptotic Rates for Manifold, Tangent Space, and Curvature Estimation

Abstract

Given an $n$-sample drawn on a submanifold $M \subset \mathbb{R}^D$, we derive optimal rates for the estimation of tangent spaces $T_X M$, the second fundamental form $II_X^M$, and the submanifold $M$. After motivating their study, we introduce a quantitative class of $\mathcal{C}^k$-submanifolds in analogy with Hölder classes. The proposed estimators are based on local polynomials and allow to deal simultaneously with the three problems at stake. Minimax lower bounds are derived using a conditional version of Assouad's lemma when the base point $X$ is random.
Fichier principal
Vignette du fichier
optimal_geometric_inference_HALv2.pdf (1.07 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-01516032 , version 1 (02-05-2017)
hal-01516032 , version 2 (24-01-2018)
hal-01516032 , version 3 (02-02-2018)

Identifiers

Cite

Eddie Aamari, Clément Levrard. Non-Asymptotic Rates for Manifold, Tangent Space, and Curvature Estimation. Annals of Statistics, 2019, 47 (1), ⟨10.1214/18-AOS1685⟩. ⟨hal-01516032v3⟩

Altmetric

Share

More