Measure estimation on manifolds: an optimal transport approach - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles Probability Theory and Related Fields Year : 2022

Measure estimation on manifolds: an optimal transport approach

Vincent Divol

Abstract

Assume that we observe i.i.d. points lying close to some unknown d-dimensional C k submanifold M in a possibly high-dimensional space. We study the problem of reconstructing the probability distribution generating the sample. After remarking that this problem is degenerate for a large class of standard losses (L p , Hellinger, total variation, etc.), we focus on the Wasserstein loss, for which we build an estimator, based on kernel density estimation, whose rate of convergence depends on d and the regularity s ≤ k − 1 of the underlying density, but not on the ambient dimension. In particular, we show that the estimator is minimax and matches previous rates in the literature in the case where the manifold M is a d-dimensional cube. The related problem of the estimation of the volume measure of M for the Wasserstein loss is also considered, for which a minimax estimator is exhibited.
Fichier principal
Vignette du fichier
wass_manifold.pdf (747.33 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03141977 , version 1 (15-02-2021)
hal-03141977 , version 2 (22-02-2022)

Identifiers

  • HAL Id : hal-03141977 , version 2

Cite

Vincent Divol. Measure estimation on manifolds: an optimal transport approach. Probability Theory and Related Fields, 2022. ⟨hal-03141977v2⟩
98 View
281 Download

Share

Gmail Mastodon Facebook X LinkedIn More