SemiDiscrete Optimal Transport: Hardness, Regularization and Numerical Solution
Abstract
Semidiscrete optimal transport problems, which evaluate the Wasserstein distance between a discrete and a generic (possibly nondiscrete) 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 #Phard. This insight prompts us to seek approximate solutions for semidiscrete 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 semidiscrete 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 semidiscrete optimal transport problems with entropic regularizers.
 Publication:

arXiv eprints
 Pub Date:
 March 2021
 arXiv:
 arXiv:2103.06263
 Bibcode:
 2021arXiv210306263T
 Keywords:

 Computer Science  Machine Learning;
 Mathematics  Optimization and Control;
 Statistics  Machine Learning