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

03/10/2021
by   Bahar Taskesen, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/12/2021

A stochastic Gauss-Newton algorithm for regularized semi-discrete optimal transport

We introduce a new second order stochastic algorithm to estimate the ent...
research
03/14/2023

Fast Regularized Discrete Optimal Transport with Group-Sparse Regularizers

Regularized discrete optimal transport (OT) is a powerful tool to measur...
research
06/02/2021

Partial Wasserstein Covering

We consider a general task called partial Wasserstein covering with the ...
research
11/13/2018

Semi-dual Regularized Optimal Transport

Variational problems that involve Wasserstein distances and more general...
research
01/23/2018

Optimal Transport on Discrete Domains

Inspired by the matching of supply to demand in logistical problems, the...
research
03/30/2021

Robustifying Conditional Portfolio Decisions via Optimal Transport

We propose a data-driven portfolio selection model that integrates side ...
research
06/28/2021

Higher-dimensional power diagrams for semi-discrete optimal transport

Efficient algorithms for solving optimal transport problems are importan...

Please sign up or login with your details

Forgot password? Click here to reset