mlsanityData to 7 Oct 2026

Wasserstein Proximal of GANs

arXiv 2102.06862 ↗First posted 13 Feb 2021cs.LG cs.AI cs.NAcited by 15

Not on the map. Why?

Abstract (arXiv)

We introduce a new method for training generative adversarial networks by applying the Wasserstein-2 metric proximal on the generators. The approach is based on Wasserstein information geometry. It defines a parametrization invariant natural gradient by pulling back optimal transport structures from probability space to parameter space. We obtain easy-to-implement iterative regularizers for the parameter updates of implicit deep generative models. Our experiments demonstrate that this method improves the speed and stability of training in terms of wall-clock time and Fr'echet Inception Distance.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 15 of its 47 references that are in the map. First posted on arXiv 13 Feb 2021.

Builds on

15 of 47 references.

References · 15

  1. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  2. 2017Improved Training of Wasserstein GANscited by 2,223
  3. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  4. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
  5. 2016InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Netscited by 858
  6. 2017Wasserstein GANcited by 635
  7. 2018A Mean Field View of the Landscape of Two-Layers Neural Networkscited by 463
  8. 2015Learning with a Wasserstein Losscited by 194
  9. 2017Stein Variational Gradient Descent as Gradient Flowcited by 149
  10. 2017On the regularization of Wasserstein GANscited by 65
  11. 2018Banach Wasserstein GANcited by 56
  12. 2013Riemannian metrics for neural networks I: feedforward networkscited by 29
3 more
  1. 2018Natural gradient via optimal transportcited by 19
  2. 2018Approximate inference with Wasserstein gradient flowscited by 12
  3. 2018Proximal Recursion for Solving the Fokker-Planck Equationcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 5; 2023: 4; 2024: 2; 2025: 0; 2026: 1.

15 papers.

Sort:

By area:

  1. 2021Optimizing Functionals on the Space of Probabilities with Input Convex Neural Networkscited by 53
  2. 2021Variational Wasserstein gradient flowcited by 53
  3. 2024Scalable Wasserstein Gradient Flow for Generative Modeling through Unbalanced Optimal Transportcited by 22
  4. 2021Efficient Gradient Flows in Sliced-Wasserstein Spacecited by 21
  5. 2022Particle-based Variational Inference with Preconditioned Functional Gradient Flowcited by 20
  6. 2022Wassmap: Wasserstein Isometric Mapping for Image Manifold Learningcited by 15
  7. 2024Wasserstein proximal operators describe score-based generative models and resolve memorizationcited by 14
  8. 2023Achieving High Accuracy with PINNs via Energy Natural Gradientscited by 10
  9. 2022Provably convergent quasistatic dynamics for mean-field two-player zero-sum gamescited by 9
  10. 2022Optimal Neural Network Approximation of Wasserstein Gradient Direction via Convex Optimizationcited by 9
  11. 2023Neural Wasserstein Gradient Flows for Maximum Mean Discrepancies with Riesz Kernelscited by 9
  12. 2022Efficient Natural Gradient Descent Methods for Large-Scale PDE-Based Optimization Problemscited by 7
3 more
  1. 2023Adaptive Annealed Importance Sampling with Constant Rate Progresscited by 7
  2. 2023Neural FIM for learning Fisher Information Metrics from point cloud datacited by 3
  3. 2026Energy Manifold Natural Gradient Descent: Riemannian Optimization for Neural PDE Solverscited by 0