mlsanityData to 7 Oct 2026

Training generative neural networks via Maximum Mean Discrepancy optimization

arXiv 1505.03906 ↗First posted 14 May 2015stat.ML cs.LGcited by 149

Not on the map. Why?

Abstract (arXiv)

We consider training a deep neural network to generate samples from an unknown distribution given i.i.d. data. We frame learning as an optimization minimizing a two-sample test statistic---informally speaking, a good generator network produces samples that cause a two-sample test to fail to reject the null hypothesis. As our two-sample test statistic, we use an unbiased estimate of the maximum mean discrepancy, which is the centerpiece of the nonparametric kernel two-sample test proposed by Gretton et al. (2012). We compare to the adversarial nets framework introduced by Goodfellow et al. (2014), in which learning is a two-player game between a generator network and an adversarial discriminator network, both trained to outwit the other. From this perspective, the MMD statistic plays the role of the discriminator. In addition to empirical comparisons, we prove bounds on the generalization error incurred by optimizing the empirical MMD.

Key facts. Cited by 149 papers in the map (data through 7 Oct 2026). First posted on arXiv 14 May 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2019: 2; 2020: 0; 2021: 32; 2022: 23; 2023: 27; 2024: 26; 2025: 22; 2026: 17.

149 papers.

Sort:

By area:

  1. 2022Generative Adversarial Networkscited by 5,603
  2. 2023One-step Diffusion with Distribution Matching Distillationcited by 978
  3. 2019A Divergence Minimization Perspective on Imitation Learning Methodscited by 188
  4. 2026Generative Modeling via Driftingcited by 98
  5. 2024Flash Diffusion: Accelerating Any Conditional Diffusion Model for Few Steps Image Generationcited by 56
  6. 2024Deep Generative Models through the Lens of the Manifold Hypothesis: A Survey and New Connectionscited by 47
  7. 2022Robust Bayesian Inference for Simulator-based Models via the MMD Posterior Bootstrapcited by 41
  8. 2021KALE Flow: A Relaxed KL Gradient Flow for Probabilities with Disjoint Supportcited by 37
  9. 2023Evading DeepFake Detectors via Adversarial Statistical Consistencycited by 37
  10. 2022SizeShiftReg: a Regularization Method for Improving Size-Generalization in Graph Neural Networkscited by 36
  11. 2023Generative Sliced MMD Flows with Riesz Kernelscited by 36
  12. 2021An error analysis of generative adversarial networks for learning distributionscited by 35
38 more
  1. 2021Probabilistic Forecasting with Generative Networks via Scoring Rule Minimizationcited by 35
  2. 2022Mirror Descent with Relative Smoothness in Measure Spaces, with application to Sinkhorn and EMcited by 33
  3. 2023On Error Propagation of Diffusion Modelscited by 30
  4. 2024DySLIM: Dynamics Stable Learning by Invariant Measure for Chaotic Systemscited by 29
  5. 2022Pre-trained Perceptual Features Improve Differentially Private Image Generationcited by 28
  6. 2021A Trust Crisis In Simulation-Based Inference? Your Posterior Approximations Can Be Unfaithfulcited by 27
  7. 2022Generative machine learning methods for multivariate ensemble post-processingcited by 26
  8. 2025Distributional Diffusion Models with Scoring Rulescited by 25
  9. 2023Evaluating the Robustness of Text-to-image Diffusion Models against Real-world Attackscited by 24
  10. 2021MaGNET: Uniform Sampling from Deep Generative Network Manifolds Without Retrainingcited by 23
  11. 2021On the capacity of deep generative networks for approximating distributionscited by 19
  12. 2021Domain-Adversarial Training of Self-Attention Based Networks for Land Cover Classification using Multi-temporal Sentinel-2 Satellite Imagerycited by 18
  13. 2024Towards Robust Graph Incremental Learning on Evolving Graphscited by 18
  14. 2025Proper scoring rules for estimation and forecast evaluationcited by 18
  15. 2025Align-Then-stEer: Adapting the Vision-Language Action Models through Unified Latent Guidancecited by 18
  16. 2021Implicit Generative Copulascited by 17
  17. 2021Composite Goodness-of-fit Tests with Kernelscited by 16
  18. 2021Graph Pooling via Coarsened Graph Infomaxcited by 15
  19. 2021Inverse design of two-dimensional materials with invertible neural networkscited by 15
  20. 2022Targeted Separation and Convergence with Kernel Discrepanciescited by 15
  21. 2023Differentially Private Neural Tangent Kernels for Privacy-Preserving Data Generationcited by 15
  22. 2026Gradient Flow Drifting: Generative Modeling via Wasserstein Gradient Flows of KDE-Approximated Divergencescited by 15
  23. 2024A Practical Guide to Sample-based Statistical Distances for Evaluating Generative Models in Sciencecited by 14
  24. 2021Rates of convergence for density estimation with generative adversarial networkscited by 13
  25. 2022Moment Matching Deep Contrastive Latent Variable Modelscited by 13
  26. 2023Optimally-Weighted Estimators of the Maximum Mean Discrepancy for Likelihood-Free Inferencecited by 13
  27. 2023MonoFlow: Rethinking Divergence GANs via the Perspective of Wasserstein Gradient Flowscited by 12
  28. 2024Online Drift Detection with Maximum Concept Discrepancycited by 12
  29. 2021Maximum Mean Discrepancy for Generalization in the Presence of Distribution and Missingness Shiftcited by 11
  30. 2024Efficient Prior Calibration From Indirect Datacited by 11
  31. 2025Scale-wise Distillation of Diffusion Modelscited by 11
  32. 2021Realizing GANs via a Tunable Loss Functioncited by 10
  33. 2021Reversible Gromov-Monge Sampler for Simulation-Based Inferencecited by 10
  34. 2024What makes an image realistic?cited by 10
  35. 2025Weighted quantization using MMD: From mean field to mean shift via gradient flowscited by 10
  36. 2026Representation Distribution Matching for One-Step Visual Generationcited by 10
  37. 2021A Pragmatic Look at Deep Imitation Learningcited by 9
  38. 2021S3RP: Self-Supervised Super-Resolution and Prediction for Advection-Diffusion Processcited by 9

50 most cited of 149 All 149 (JSON)