Beyond entropic regularization: Debiased Gaussian estimators for discrete optimal transport and general linear programs

TL;DR

This paper introduces debiased Gaussian estimators for discrete optimal transport that achieve asymptotic normality centered at the true solution, outperforming existing biased estimators based on entropic regularization.

Contribution

The authors develop a novel regularization and debiasing method for optimal transport estimators, avoiding bias correction and extending to general linear programs.

Findings

Estimators have Gaussian limits centered at the true solution.

The proposed method outperforms entropic regularization-based estimators.

Simulation and data analysis demonstrate improved accuracy and inference.

Abstract

This work proposes new estimators for discrete optimal transport plans that enjoy Gaussian limits centered at the true solution. This behavior stands in stark contrast with the performance of existing estimators, including those based on entropic regularization, which are asymptotically biased and only satisfy a CLT centered at a regularized version of the population-level plan. We develop a new regularization approach based on a different class of penalty functions, which can be viewed as the duals of those previously considered in the literature. The key feature of these penalty schemes it that they give rise to preliminary estimates that are asymptotically linear in the penalization strength. Our final estimator is obtained by constructing an appropriate linear combination of two penalized solutions corresponding to two different tuning parameters so that the bias introduced by the penalization cancels out. Unlike classical debiasing procedures, therefore, our proposal entirely avoids the delicate problem of estimating and then subtracting the estimated bias term. Our proofs, which apply beyond the case of optimal transport, are based on a novel asymptotic analysis of penalization schemes for linear programs. As a corollary of our results, we obtain the consistency of the naive bootstrap for fully data-driven inference on the true optimal solution. Simulation results and two data analyses support strongly the benefits of our approach relative to existing techniques.