MinMax Methods for Optimal Transport and Beyond: Regularization, Approximation and Numerics

10/22/2020
by   Luca De Gennaro Aquino, et al.
0

We study MinMax solution methods for a general class of optimization problems related to (and including) optimal transport. Theoretically, the focus is on fitting a large class of problems into a single MinMax framework and generalizing regularization techniques known from classical optimal transport. We show that regularization techniques justify the utilization of neural networks to solve such problems by proving approximation theorems and illustrating fundamental issues if no regularization is used. We further study the relation to the literature on generative adversarial nets, and analyze which algorithmic techniques used therein are particularly suitable to the class of problems studied in this paper. Several numerical experiments showcase the generality of the setting and highlight which theoretical insights are most beneficial in practice.

READ FULL TEXT

page 1

page 2

page 3

page 4

02/23/2018

Computation of optimal transport and related hedging problems via penalization and neural networks

This paper presents a widely applicable approach to solving (multi-margi...
03/02/2020

Optimal transport: discretization and algorithms

This chapter describes techniques for the numerical resolution of optima...
10/04/2022

Tikhonov Regularization is Optimal Transport Robust under Martingale Constraints

Distributionally robust optimization has been shown to offer a principle...
12/10/2020

Hardness results for Multimarginal Optimal Transport problems

Multimarginal Optimal Transport (MOT) is the problem of linear programmi...
09/29/2022

Improving Generative Flow Networks with Path Regularization

Generative Flow Networks (GFlowNets) are recently proposed models for le...
09/13/2021

On the regularized risk of distributionally robust learning over deep neural networks

In this paper we explore the relation between distributionally robust le...
07/26/2022

The derivatives of Sinkhorn-Knopp converge

We show that the derivatives of the Sinkhorn-Knopp algorithm, or iterati...