Statistical Estimation of Monge Transport Maps via Brenier Potentials

TL;DR

This paper presents a new statistical estimator for Monge transport maps based on Brenier potentials, applicable to finite samples without requiring smoothness, with proven convergence rates.

Contribution

It introduces a Brenier potential-based estimator for Monge maps from finite samples, with convergence analysis and applicability to semi-discrete cases.

Findings

Estimator has a simple closed-form expression.

Convergence rates are established for the estimator.

Sharper rates are achieved in semi-discrete settings.

Abstract

We introduce and analyze a statistical estimator for Monge transport maps: solutions to the quadratic optimal transport problem in Euclidean space. For absolutely continuous source measures, this map is uniquely defined as the gradient of a convex function, a result known as Brenier's theorem. Without absolute continuity, the problem is relaxed, maps are replaced by coupling measures, and optimal couplings are supported on the subdifferential of a convex function, a Brenier potential. This characterization is the basis for our statistical estimator of Monge transport maps for measures known only through finite samples. The resulting Brenier potential has a simple closed-form expression based on the dual solution of the discrete sampled problem. In particular, our methodology does not rely on smoothness or continuity of the Monge transport map and requires no computation beyond primal-dual solutions of the discrete finite-dimensional problem. We exhibit convergence rates for this estimator based on a new error bound for the quadratic optimal transport problem. In the semi-discrete setting, where the target measure is finitely supported, our estimator enjoys sharper convergence rates. Finally, using similar proof techniques, we provide a novel convergence rate for empirical couplings.