Measure estimation on manifolds: an optimal transport approach

TL;DR

This paper develops a Wasserstein-based estimator for probability distributions near unknown manifolds, achieving minimax rates that depend on the manifold's intrinsic dimension and density regularity, not on ambient space dimension.

Contribution

It introduces a kernel density estimator optimized for Wasserstein loss on manifold-supported data, with proven minimax optimality and dimension-independent convergence rates.

Findings

Estimator achieves minimax optimal rates.

Convergence depends on manifold dimension and density smoothness.

Method is effective for high-dimensional ambient spaces.

Abstract

Assume that we observe i.i.d.~points lying close to some unknown $d$-dimensional $\mathcal{C}^k$ 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 $s\leq k-1$ 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.