Lune

NeurIPS2020Top-tier venue

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

Luca De Gennaro Aquino, Stephan Eckstein

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.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

Builds onCited byLeft to right by year; the more cited, the higher.

Builds on4

  1. On Solving Minimax Optimization Locally: A Follow-the-Ridge ApproachYuanhao Wang, Guodong Zhang, Jimmy BaICLR 2020 · 106 citations
  2. On Unbalanced Optimal Transport: An Analysis of Sinkhorn AlgorithmKhiem Pham, Khang Le, Nhat Ho, Tung Pham et al.ICML 2020 · 104 citations
  3. Small-GAN: Speeding up GAN Training using Core-SetsSamarth Sinha, Han Zhang, Anirudh Goyal, Yoshua Bengio et al.ICML 2020 · 87 citations
  4. Projection Robust Wasserstein Distance and Riemannian OptimizationTianyi Lin, Chenyou Fan, Nhat Ho, Marco Cuturi et al.NeurIPS 2020 · 84 citations

Related papers

  1. A Statistical Learning Perspective on Semi-dual Adversarial Neural Optimal Transport SolversRoman Tarasov, Petr Mokrov, Milena Gazdieva, Evgeny Burnaev et al.ICLR 2026 · 2 citations
  2. Optimal transport mapping via input convex neural networksAshok Vardhan Makkuva, Amirhossein Taghvaei, Sewoong Oh, Jason D. LeeICML 2020 · 254 citations
  3. Recovery Bounds on Class-Based Optimal Transport: A Sum-of-Norms Regularization FrameworkArman Rahbar, Ashkan Panahi, Morteza Haghir Chehreghani, Devdatt P. Dubhashi et al.ICML 2023
  4. Entropic Neural Optimal Transport via Diffusion ProcessesNikita Gushchin, Alexander Kolesov, Alexander Korotin, Dmitry P. Vetrov et al.NeurIPS 2023 · 59 citations
  5. Expectile Regularization for Fast and Accurate Training of Neural Optimal TransportNazar Buzun, Maksim Bobrin, Dmitry V. DylovNeurIPS 2024
Dusk over the sea between two cliffs drawn in fine vertical lines