Sparse Regularized Optimal Transport without Curse of Dimensionality

TL;DR

This paper demonstrates that certain regularized optimal transport problems, including less-smooth divergences like Tsallis divergence, can achieve dimension-independent parametric convergence rates, challenging the belief that they suffer from the curse of dimensionality.

Contribution

It proves that for a broad family of divergences, empirical quantities in regularized optimal transport converge at the parametric rate regardless of dimension, with new CLTs for key quantities.

Findings

Empirical convergence rates are dimension-independent.

Central limit theorems established for cost, coupling, and dual potentials.

Refutes the belief that less-smooth divergences suffer from curse of dimensionality.

Abstract

Entropic optimal transport -- the optimal transport problem regularized by KL diver\-gence -- is highly successful in statistical applications. Thanks to the smoothness of the entropic coupling, its sample complexity avoids the curse of dimensionality suffered by unregularized optimal transport. The flip side of smoothness is overspreading: the entropic coupling always has full support, whereas the unregularized coupling that it approximates is usually sparse, even given by a map. Regularizing optimal transport by less-smooth $f$-divergences such as Tsallis divergence (i.e., $L^p$-regularization) is known to allow for sparse approximations, but is often thought to suffer from the curse of dimensionality as the couplings have limited differentiability and the dual is not strongly concave. We refute this conventional wisdom and show, for a broad family of divergences, that the key empirical quantities converge at the parametric rate, independently of the dimension. More precisely, we provide central limit theorems for the optimal cost, the optimal coupling, and the dual potentials induced by i.i.d.\ samples from the marginals. These results are obtained by a powerful yet elementary approach that is of broader interest for Z-estimation in function classes that are not Donsker.