mlsanityData to 7 Oct 2026

Smoothness and Stability in GANs

arXiv 2002.04185 ↗First posted 11 Feb 2020cs.LG stat.MLcited by 27

Not on the map. Why?

Abstract (arXiv)

Generative adversarial networks, or GANs, commonly display unstable behavior during training. In this work, we develop a principled theoretical framework for understanding the stability of various types of GANs. In particular, we derive conditions that guarantee eventual stationarity of the generator when it is trained with gradient descent, conditions that must be satisfied by the divergence that is minimized by the GAN and the generator's architecture. We find that existing GAN variants satisfy some, but not all, of these conditions. Using tools from convex analysis, optimal transport, and reproducing kernels, we construct a GAN that fulfills these conditions simultaneously. In the process, we explain and clarify the need for various existing GAN stabilization techniques, including Lipschitz constraints, gradient penalties, and smooth activation functions.

Key facts. Cited by 27 papers in the map (data through 7 Oct 2026). First posted on arXiv 11 Feb 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 6; 2023: 5; 2024: 4; 2025: 5; 2026: 1.

27 papers.

Sort:

By area:

  1. 2022A Closer Look at Smoothness in Domain Adversarial Trainingcited by 85
  2. 2023Diffusion Models for Time Series Applications: A Surveycited by 72
  3. 2021Generative Adversarial Registration for Improved Conditional Deformable Templatescited by 31
  4. 2021CarveMix: A Simple Data Augmentation Method for Brain Lesion Segmentationcited by 30
  5. 2022Diagnosing and Fixing Manifold Overfitting in Deep Generative Modelscited by 28
  6. 2023Regular Time-series Generation using SGMcited by 23
  7. 2024Wasserstein Gradient Flows for Moreau Envelopes of f-Divergences in Reproducing Kernel Hilbert Spacescited by 15
  8. 2021Manifold Learning Benefits GANscited by 14
  9. 2023SAN: Inducing Metrizability of GAN with Discriminative Normalized Linear Layercited by 14
  10. 2025UniGuardian: A Unified Defense for Detecting Prompt Injection, Backdoor Attacks and Adversarial Attacks in Large Language Modelscited by 12
  11. 2021Re-using Adversarial Mask Discriminators for Test-time Training under Distribution Shiftscited by 7
  12. 2022Continuous and Distribution-free Probabilistic Wind Power Forecasting: A Conditional Normalizing Flow Approachcited by 7
15 more
  1. 2022Gromov-Wasserstein Autoencoderscited by 7
  2. 2024Unknown Domain Inconsistency Minimization for Domain Generalizationcited by 7
  3. 2021Stop Throwing Away Discriminators! Re-using Adversaries for Test-Time Trainingcited by 4
  4. 2022Invariant Representations with Stochastically Quantized Neural Networkscited by 4
  5. 2025TSGM: Regular and Irregular Time-series Generation using Score-based Generative Modelscited by 3
  6. 2021Generalization of GANs and overparameterized models under Lipschitz continuitycited by 2
  7. 2024CHAIN: Enhancing Generalization in Data-Efficient GANs via lipsCHitz continuity constrAIned Normalizationcited by 2
  8. 2023Sit Back and Relax: Learning to Drive Incrementally in All Weather Conditionscited by 1
  9. 2024Novel Hybrid Integrated Pix2Pix and WGAN Model with Gradient Penalty for Binary Images Denoisingcited by 1
  10. 2022Unified Perspective on Probability Divergence via Maximum Likelihood Density Ratio Estimation: Bridging KL-Divergence and Integral Probability Metricscited by 0
  11. 2023Convergences for Minimax Optimization Problems over Infinite-Dimensional Spaces Towards Stability in Adversarial Trainingcited by 0
  12. 2025Nested Annealed Training Scheme for Generative Adversarial Networkscited by 0
  13. 2025SONA: Learning Conditional, Unconditional, and Mismatching-Aware Discriminatorcited by 0
  14. 2025Effective Series Decomposition and Components Learning for Time Series Generationcited by 0
  15. 2026Representation-driven Endoscopic Visual Embedding Alignment for Latent Generationcited by 0