# On Convergence and Stability of GANs

arXiv: https://arxiv.org/abs/1705.07215 · HTML: https://mlsanity.com/paper/1705.07215/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 May 2017.

## Built on by (most cited first, 18 of 18)

- [Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flow](https://mlsanity.com/paper/1810.00821/) (2018)
- [Revisiting Discriminator in GAN Compression: A Generator-discriminator Cooperative Compression Scheme](https://mlsanity.com/paper/2110.14439/) (2021)
- [MEGAN: Mixture of Experts of Generative Adversarial Networks for Multimodal Image Generation](https://mlsanity.com/paper/1805.02481/) (2018)
- [Lipschitzness Is All You Need To Tame Off-policy Generative Adversarial Imitation Learning](https://mlsanity.com/paper/2006.16785/) (2020)
- [Instability and Local Minima in GAN Training with Kernel Discriminators](https://mlsanity.com/paper/2208.09938/) (2022)
- [DigGAN: Discriminator gradIent Gap Regularization for GAN Training with Limited Data](https://mlsanity.com/paper/2211.14694/) (2022)
- [DEQGAN: Learning the Loss Function for PINNs with Generative Adversarial Networks](https://mlsanity.com/paper/2209.07081/) (2022)
- [Guiding GANs: How to control non-conditional pre-trained GANs for conditional image generation](https://mlsanity.com/paper/2101.00990/) (2021)
- [Learning Distributions by Generative Adversarial Networks: Approximation and Generalization](https://mlsanity.com/paper/2205.12601/) (2022)
- [Performative Drift Resistant Classification Using Generative Domain Adversarial Networks](https://mlsanity.com/paper/2504.01135/) (2025)
- [MAGIC: Few-Shot Mask-Guided Anomaly Inpainting with Prompt Perturbation, Spatially Adaptive Guidance, and Context Awareness](https://mlsanity.com/paper/2507.02314/) (2025)
- [Effective Shortcut Technique for GAN](https://mlsanity.com/paper/2201.11351/) (2022)
- [How to train your draGAN: A task oriented solution to imbalanced classification](https://mlsanity.com/paper/2211.10065/) (2022)
- [Multispectral Contrastive Learning with Viewmaker Networks](https://mlsanity.com/paper/2302.05757/) (2023)
- [Flooding Regularization for Stable Training of Generative Adversarial Networks](https://mlsanity.com/paper/2311.00318/) (2023)
- [On depth prediction for autonomous driving using self-supervised learning](https://mlsanity.com/paper/2403.06194/) (2024)
- [Multi-Armed Bandit Approach for Optimizing Training on Synthetic Data](https://mlsanity.com/paper/2412.05466/) (2024)
- [A Wasserstein GAN-based climate scenario generator for risk management and insurance: the case of soil subsidence](https://mlsanity.com/paper/2605.06678/) (2026)

## Abstract (arXiv)

We propose studying GAN training dynamics as regret minimization, which is in contrast to the popular view that there is consistent minimization of a divergence between real and generated distributions. We analyze the convergence of GAN training from this new point of view to understand why mode collapse happens. We hypothesize the existence of undesirable local equilibria in this non-convex game to be responsible for mode collapse. We observe that these local equilibria often exhibit sharp gradients of the discriminator function around some real data points. We demonstrate that these degenerate local equilibria can be avoided with a gradient penalty scheme called DRAGAN. We show that DRAGAN enables faster training, achieves improved stability with fewer mode collapses, and leads to generator networks with better modeling performance across a variety of architectures and objective functions.