Semi-Discrete Optimal Transport: Hardness, Regularization and Numerical Solution

TL;DR

This paper investigates the computational hardness of semi-discrete optimal transport, proves a specific problem is #P-hard, and introduces regularization and robust methods with improved algorithms for practical solutions.

Contribution

It provides the first theoretical hardness proof for a semi-discrete optimal transport problem and develops regularization techniques linked to ambiguity sets, enhancing solution efficiency.

Findings

Proved #P-hardness for a specific semi-discrete optimal transport problem.

Linked regularization schemes to ambiguity sets in distributionally robust optimization.

Developed a stochastic gradient descent algorithm with improved convergence guarantees.

Abstract

Semi-discrete optimal transport problems, which evaluate the Wasserstein distance between a discrete and a generic (possibly non-discrete) probability measure, are believed to be computationally hard. Even though such problems are ubiquitous in statistics, machine learning and computer vision, however, this perception has not yet received a theoretical justification. To fill this gap, we prove that computing the Wasserstein distance between a discrete probability measure supported on two points and the Lebesgue measure on the standard hypercube is already #P-hard. This insight prompts us to seek approximate solutions for semi-discrete optimal transport problems. We thus perturb the underlying transportation cost with an additive disturbance governed by an ambiguous probability distribution, and we introduce a distributionally robust dual optimal transport problem whose objective function is smoothed with the most adverse disturbance distributions from within a given ambiguity set. We further show that smoothing the dual objective function is equivalent to regularizing the primal objective function, and we identify several ambiguity sets that give rise to several known and new regularization schemes. As a byproduct, we discover an intimate relation between semi-discrete optimal transport problems and discrete choice models traditionally studied in psychology and economics. To solve the regularized optimal transport problems efficiently, we use a stochastic gradient descent algorithm with imprecise stochastic gradient oracles. A new convergence analysis reveals that this algorithm improves the best known convergence guarantee for semi-discrete optimal transport problems with entropic regularizers.