mlsanityData to 7 Oct 2026

Generalization and Equilibrium in Generative Adversarial Nets (GANs)

arXiv 1703.00573 ↗First posted 2 Mar 2017cs.LG cs.NE stat.MLcited by 165

Not on the map. Why?

Abstract (arXiv)

We show that training of generative adversarial network (GAN) may not have good generalization properties; e.g., training may appear successful but the trained distribution may be far from target distribution in standard metrics. However, generalization does occur for a weaker metric called neural net distance. It is also shown that an approximate pure equilibrium exists in the discriminator/generator game for a special class of generators with natural training objectives when generator capacity and training set sizes are moderate. This existence of equilibrium inspires MIX+GAN protocol, which can be combined with any existing GAN training, and empirically shown to improve some of them.

Key facts. Cited by 165 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Mar 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2019: 3; 2020: 1; 2021: 47; 2022: 33; 2023: 42; 2024: 21; 2025: 10; 2026: 8.

165 papers.

Sort:

By area:

  1. 2023Inversion by Direct Iteration: An Alternative to Denoising Diffusion for Image Restorationcited by 164
  2. 2021OpenGAN: Open-Set Recognition via Open Data Generationcited by 135
  3. 2024Why Tabular Foundation Models Should Be a Research Prioritycited by 103
  4. 2019Provably Efficient Imitation Learning from Observation Alonecited by 78
  5. 2023Membership Inference Attacks against Synthetic Data through Overfitting Detectioncited by 66
  6. 2022Verifying the Union of Manifolds Hypothesis for Image Datacited by 62
  7. 2021MG-GAN: A Multi-Generator Model Preventing Out-of-Distribution Samples in Pedestrian Trajectory Predictioncited by 61
  8. 2022Transferability in Deep Learning: A Surveycited by 57
  9. 2021Variational Wasserstein gradient flowcited by 53
  10. 2024Breaking the Curse of Dimensionality: Diffusion Models Efficiently Learn Low-Dimensional Distributionscited by 53
  11. 2024Deep Generative Models through the Lens of the Manifold Hypothesis: A Survey and New Connectionscited by 47
  12. 2021An error analysis of generative adversarial networks for learning distributionscited by 35
38 more
  1. 2021Quantifying and Improving Transferability in Domain Generalizationcited by 35
  2. 2024AI and the Problem of Knowledge Collapsecited by 34
  3. 2023Free Lunch for Domain Adversarial Training: Environment Label Smoothingcited by 33
  4. 2021Property Inference Attacks Against GANscited by 32
  5. 2021Tractable Density Estimation on Learned Manifolds with Conformal Embedding Flowscited by 30
  6. 2023On the Generalization of Diffusion Modelcited by 30
  7. 2023Beyond Privacy: Navigating the Opportunities and Challenges of Synthetic Datacited by 29
  8. 2022Diagnosing and Fixing Manifold Overfitting in Deep Generative Modelscited by 28
  9. 2020On Computation and Generalization of Generative Adversarial Imitation Learningcited by 27
  10. 2021Outlier-Robust Optimal Transport: Duality, Structure, and Statistical Analysiscited by 27
  11. 2022Multi-Source Unsupervised Domain Adaptation via Pseudo Target Domaincited by 27
  12. 2021Conditional Image Generation by Conditioning Variational Auto-Encoderscited by 25
  13. 2021This Person (Probably) Exists. Identity Membership Attacks Against GAN Generated Facescited by 25
  14. 2022Difficulty-Aware Simulator for Open Set Recognitioncited by 24
  15. 2021A Neural Tangent Kernel Perspective of GANscited by 21
  16. 2024A Survey on Statistical Theory of Deep Learning: Approximation, Training Dynamics, and Generative Modelscited by 20
  17. 2021Deep Extrapolation for Attribute-Enhanced Generationcited by 18
  18. 2024Deep MMD Gradient Flow without adversarial trainingcited by 18
  19. 2021Wasserstein Generative Adversarial Uncertainty Quantification in Physics-Informed Neural Networkscited by 16
  20. 2022What is a Good Metric to Study Generalization of Minimax Learners?cited by 16
  21. 2023Statistical Guarantees for Variational Autoencoders using PAC-Bayesian Theorycited by 16
  22. 2021Smooth p-Wasserstein Distance: Structure, Empirical Approximation, and Statistical Applicationscited by 15
  23. 2021Non-Asymptotic Performance Guarantees for Neural Estimation of mathsff-Divergencescited by 15
  24. 2021Applications of Generative Adversarial Networks in Anomaly Detection: A Systematic Literature Reviewcited by 15
  25. 2022UDoc-GAN: Unpaired Document Illumination Correction with Background Light Priorcited by 15
  26. 2024Off-Dynamics Reinforcement Learning via Domain Adaptation and Reward Augmented Imitationcited by 15
  27. 2021Reducing bias and increasing utility by federated generative modeling of medical images using a centralized adversarycited by 14
  28. 2021Understanding Overparameterization in Generative Adversarial Networkscited by 14
  29. 2023SAN: Inducing Metrizability of GAN with Discriminative Normalized Linear Layercited by 14
  30. 2025Simulating the Real World: A Unified Survey of Multimodal Generative Modelscited by 14
  31. 2022A review of Generative Adversarial Networks for Electronic Health Records: applications, evaluation measures and data sourcescited by 13
  32. 2023PAC-Bayesian Generalization Bounds for Adversarial Generative Modelscited by 13
  33. 2021A likelihood approach to nonparametric estimation of a singular distribution using deep generative modelscited by 12
  34. 2023On Deep Generative Models for Approximation and Estimation of Distributions on Manifoldscited by 12
  35. 2021Exposing Previously Undetectable Faults in Deep Neural Networkscited by 11
  36. 2023Statistical Complexity of Quantum Learningcited by 11
  37. 2021Realizing GANs via a Tunable Loss Functioncited by 10
  38. 2021Lifelong Mixture of Variational Autoencoderscited by 10

50 most cited of 165 All 165 (JSON)