Entropic estimation of optimal transport maps

TL;DR

This paper introduces an efficient, scalable method for estimating optimal transport maps using entropic regularization and Sinkhorn's algorithm, with theoretical guarantees and adaptive smoothing capabilities.

Contribution

It proposes a novel entropic approach to estimate optimal transport maps that is computationally efficient, parallelizable, and comes with finite-sample guarantees.

Findings

Method is faster and scalable for large datasets.

Estimator achieves comparable statistical performance to existing methods.

Adaptive version improves estimation based on map smoothness.

Abstract

We develop a computationally tractable method for estimating the optimal map between two distributions over $\mathbb{R}^d$ with rigorous finite-sample guarantees. Leveraging an entropic version of Brenier's theorem, we show that our estimator -- the \emph{barycentric projection} of the optimal entropic plan -- is easy to compute using Sinkhorn's algorithm. As a result, unlike current approaches for map estimation, which are slow to evaluate when the dimension or number of samples is large, our approach is parallelizable and extremely efficient even for massive data sets. Under smoothness assumptions on the optimal map, we show that our estimator enjoys comparable statistical performance to other estimators in the literature, but with much lower computational cost. We showcase the efficacy of our proposed estimator through numerical examples, even ones not explicitly covered by our assumptions. By virtue of Lepski's method, we propose a modified version of our estimator that is adaptive to the smoothness of the underlying optimal transport map. Our proofs are based on a modified duality principle for entropic optimal transport and on a method for approximating optimal entropic plans due to Pal (2019).