mlsanityData to 14 Oct 2026

Towards Principled Methods for Training Generative Adversarial Networks

arXiv 1701.04862 ↗First posted 17 Jan 2017stat.ML cs.LGcited by 464

Not on the map. Why?

Cited by 55 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

The goal of this paper is not to introduce a single algorithm or method, but to make theoretical steps towards fully understanding the training dynamics of generative adversarial networks. In order to substantiate our theoretical analysis, we perform targeted experiments to verify our assumptions, illustrate our claims, and quantify the phenomena. This paper is divided into three sections. The first section introduces the problem at hand. The second section is dedicated to studying and proving rigorously the problems including instability and saturation that arize when training generative adversarial networks. The third section examines a practical and theoretically grounded direction towards solving these problems, while introducing new tools to study them.

Key facts. Cited by 464 papers in the map (data through 14 Oct 2026). First posted on arXiv 17 Jan 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2018: 2; 2019: 1; 2020: 5; 2021: 126; 2022: 100; 2023: 80; 2024: 63; 2025: 52; 2026: 35.

464 papers.

Sort:

By area:

  1. 2022Diffusion Models in Vision: A Surveycited by 1,015
  2. 2023LayoutDiffusion: Controllable Diffusion Model for Layout-to-image Generationcited by 259
  3. 2021Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Modelscited by 252
  4. 2021Projected GANs Converge Fastercited by 208
  5. 2022Diffusion-GAN: Training GANs with Diffusioncited by 205
  6. 2021ST++: Make Self-training Work Better for Semi-supervised Semantic Segmentationcited by 184
  7. 2022Correct-N-Contrast: A Contrastive Approach for Improving Robustness to Spurious Correlationscited by 172
  8. 2021A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challengescited by 154
  9. 2023A Survey of Imitation Learning: Algorithms, Recent Developments, and Challengescited by 148
  10. 2022StyleGAN-Human: A Data-Centric Odyssey of Human Generationcited by 144
  11. 2023Diffused Heads: Diffusion Models Beat GANs on Talking-Face Generationcited by 142
  12. 2021Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesiscited by 140
38 more
  1. 2022SE(3)-DiffusionFields: Learning smooth cost functions for joint grasp and motion optimization through diffusioncited by 127
  2. 2022Differentially Private Diffusion Modelscited by 119
  3. 2018Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flowcited by 105
  4. 2021Deep Generative Models in Engineering Design: A Reviewcited by 105
  5. 2021An Introduction to Deep Generative Modelingcited by 104
  6. 2021Generative Modeling with Optimal Transport Mapscited by 82
  7. 2023NeuralField-LDM: Scene Generation with Hierarchical Latent Diffusion Modelscited by 76
  8. 2021Enhancing Photorealism Enhancementcited by 74
  9. 2020Fighting Copycat Agents in Behavioral Cloning from Observation Historiescited by 71
  10. 2022Towards Implicit Text-Guided 3D Shape Generationcited by 68
  11. 2021Generating Smooth Pose Sequences for Diverse Human Motion Predictioncited by 66
  12. 2021Risk-Averse Offline Reinforcement Learningcited by 65
  13. 2021GANs for Medical Image Synthesis: An Empirical Studycited by 65
  14. 2021Learning Probabilistic Ordinal Embeddings for Uncertainty-Aware Regressioncited by 58
  15. 2021Data-Efficient Instance Generation from Instance Discriminationcited by 58
  16. 2021Reverse Engineering of Generative Models: Inferring Model Hyperparameters from Generated Imagescited by 58
  17. 2021Rebooting ACGAN: Auxiliary Classifier GANs with Stable Trainingcited by 57
  18. 2022High-resolution Face Swapping via Latent Semantics Disentanglementcited by 57
  19. 2021Don't Generate Me: Training Differentially Private Generative Models with Sinkhorn Divergencecited by 54
  20. 2021Deceive D: Adaptive Pseudo Augmentation for GAN Training with Limited Datacited by 53
  21. 2022Entropic Neural Optimal Transport via Diffusion Processescited by 50
  22. 2023Vector Quantized Time Series Generation with a Bidirectional Prior Modelcited by 50
  23. 2025Distribution Matching Distillation Meets Reinforcement Learningcited by 50
  24. 2023Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Modelscited by 49
  25. 2021Adversarially Guided Actor-Criticcited by 47
  26. 2021Posterior Meta-Replay for Continual Learningcited by 45
  27. 2022Learning Agile Skills via Adversarial Imitation of Rough Partial Demonstrationscited by 45
  28. 2023Instant3D: Instant Text-to-3D Generationcited by 45
  29. 2024Exploring Diverse Methods in Visual Question Answeringcited by 45
  30. 2025Dataset Distillation with Neural Characteristic Function: A Minmax Perspectivecited by 45
  31. 2023Identifying Spurious Biases Early in Training through the Lens of Simplicity Biascited by 44
  32. 2022Modeling Image Composition for Complex Scene Generationcited by 43
  33. 2019Random Expert Distillation: Imitation Learning via Expert Policy Support Estimationcited by 42
  34. 2022Truncated Diffusion Probabilistic Models and Diffusion-based Adversarial Auto-Encoderscited by 42
  35. 2021Context-Aware Layout to Image Generation with Enhanced Object Appearancecited by 41
  36. 2022Data Augmentation techniques in time series domain: A survey and taxonomycited by 41
  37. 2022Can Push-forward Generative Models Fit Multimodal Distributions?cited by 41
  38. 2024Language Generation in the Limitcited by 40

50 most cited of 464 All 464 (JSON)