MinMax Methods for Optimal Transport and Beyond: Regularization, Approximation and Numerics
From MaRDI portal
Publication:6351962
arXiv2010.11502MaRDI QIDQ6351962
Stephan Eckstein, Luca De Gennaro Aquino
Publication date: 22 October 2020
Abstract: 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.
Has companion code repository: https://github.com/stephaneckstein/minmaxot
This page was built for publication: MinMax Methods for Optimal Transport and Beyond: Regularization, Approximation and Numerics
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6351962)
