mlsanityData to 7 Oct 2026

On gradient regularizers for MMD GANs

arXiv 1805.11565 ↗First posted 29 May 2018stat.ML cs.LGcited by 28

Not on the map. Why?

Abstract (arXiv)

We propose a principled method for gradient-based regularization of the critic of GAN-like models trained by adversarially optimizing the kernel of a Maximum Mean Discrepancy (MMD). We show that controlling the gradient of the critic is vital to having a sensible loss function, and devise a method to enforce exact, analytical gradient constraints at no additional cost compared to existing approximate techniques based on additive regularizers. The new loss function is provably continuous, and experiments show that it stabilizes and accelerates training, giving image generation models that outperform state-of-the art methods on 160 × 160 CelebA and 64 × 64 unconditional ImageNet.

Key facts. Cited by 28 papers in the map (data through 7 Oct 2026). First posted on arXiv 29 May 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 10; 2022: 3; 2023: 5; 2024: 2; 2025: 6; 2026: 1.

28 papers.

Sort:

By area:

  1. 2021Deep Generative Learning via Schr"odinger Bridgecited by 103
  2. 2023Optimizing DDPM Sampling with Shortcut Fine-Tuningcited by 81
  3. 2021Variational Wasserstein gradient flowcited by 53
  4. 2021RoMA: Robust Model Adaptation for Offline Model-based Optimizationcited by 39
  5. 2022Why neural networks find simple solutions: the many regularizers of geometric complexitycited by 38
  6. 2021KALE Flow: A Relaxed KL Gradient Flow for Probabilities with Disjoint Supportcited by 37
  7. 2020On Computation and Generalization of Generative Adversarial Imitation Learningcited by 27
  8. 2021Disentangled Recurrent Wasserstein Autoencodercited by 22
  9. 2024Deep MMD Gradient Flow without adversarial trainingcited by 18
  10. 2023Differentially Private Neural Tangent Kernels for Privacy-Preserving Data Generationcited by 15
  11. 2021Controlling Wasserstein Distances by Kernel Norms with Application to Compressive Statistical Learningcited by 13
  12. 2021The Geometric Occam's Razor Implicit in Deep Learningcited by 7
16 more
  1. 2022Evaluating Graph Generative Models with Contrastively Learned Featurescited by 5
  2. 2021DuelGAN: A Duel Between Two Discriminators Stabilizes the GAN Trainingcited by 4
  3. 2021Adversarially Robust Kernel Smoothingcited by 4
  4. 2022Multi-level Latent Space Structuring for Generative Controlcited by 4
  5. 2025Optimality and Adaptivity of Deep Neural Features for Instrumental Variable Regressioncited by 3
  6. 2026Sobolev Regularized MMD Gradient Flowcited by 3
  7. 2021Learning High-Dimensional Distributions with Latent Neural Fokker-Planck Kernelscited by 2
  8. 2023Data Interpolants -- That's What Discriminators in Higher-order Gradient-regularized GANs Arecited by 2
  9. 2024Learning Representations for Independence Testingcited by 2
  10. 2025Stationary MMD Pointscited by 2
  11. 2023Hoeffding's Inequality for Markov Chains under Generalized Concentrability Conditioncited by 1
  12. 2023Stability Analysis Framework for Particle-based Distance GANs with Wasserstein Gradient Flowcited by 0
  13. 2025CKGAN: Training Generative Adversarial Networks Using Characteristic Kernel Integral Probability Metricscited by 0
  14. 2025Smooth Model Compression without Fine-Tuningcited by 0
  15. 2025Exploring Image Generation via Mutually Exclusive Probability Spaces and Local Correlation Hypothesiscited by 0
  16. 2025Adaptive generative moment matching networks for improved learning of dependence structurescited by 0