# GANs May Have No Nash Equilibria

arXiv: https://arxiv.org/abs/2002.09124 · HTML: https://mlsanity.com/paper/2002.09124/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Feb 2020.

## Built on by (most cited first, 20 of 20)

- [Sig-Wasserstein GANs for Time Series Generation](https://mlsanity.com/paper/2111.01207/) (2021)
- [Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances](https://mlsanity.com/paper/2111.00418/) (2021)
- [Closed-Loop Data Transcription to an LDR via Minimaxing Rate Reduction](https://mlsanity.com/paper/2111.06636/) (2021)
- [Data synthesis and adversarial networks: A review and meta-analysis in cancer imaging](https://mlsanity.com/paper/2107.09543/) (2021)
- [A survey on GANs for computer vision: Recent research, analysis and taxonomy](https://mlsanity.com/paper/2203.11242/) (2022)
- [Understanding Overparameterization in Generative Adversarial Networks](https://mlsanity.com/paper/2104.05605/) (2021)
- [Solving a class of non-convex min-max games using adaptive momentum methods](https://mlsanity.com/paper/2104.12676/) (2021)
- [The Representation Jensen-Shannon Divergence](https://mlsanity.com/paper/2305.16446/) (2023)
- [Solving Min-Max Optimization with Hidden Structure via Gradient Descent Ascent](https://mlsanity.com/paper/2101.05248/) (2021)
- [Nonconvex-Nonconcave Min-Max Optimization with a Small Maximization Domain](https://mlsanity.com/paper/2110.03950/) (2021)
- [DO-GAN: A Double Oracle Framework for Generative Adversarial Networks](https://mlsanity.com/paper/2102.08577/) (2021)
- [Game of GANs: Game-Theoretical Models for Generative Adversarial Networks](https://mlsanity.com/paper/2106.06976/) (2021)
- [Pursuit of a Discriminative Representation for Multiple Subspaces via Sequential Games](https://mlsanity.com/paper/2206.09120/) (2022)
- [PRISM: Privacy-Preserving Improved Stochastic Masking for Federated Generative Models](https://mlsanity.com/paper/2503.08085/) (2025)
- [Are conditional GANs explicitly conditional?](https://mlsanity.com/paper/2106.15011/) (2021)
- [MEGA: Model Stealing via Collaborative Generator-Substitute Networks](https://mlsanity.com/paper/2202.00008/) (2022)
- [Rethinking Teacher-Student Curriculum Learning through the Cooperative Mechanics of Experience](https://mlsanity.com/paper/2404.03084/) (2024)
- [Sample-efficient Quantum Born Machine through Coding Rate Reduction](https://mlsanity.com/paper/2211.10418/) (2022)
- [On depth prediction for autonomous driving using self-supervised learning](https://mlsanity.com/paper/2403.06194/) (2024)
- [Double Oracle Neural Architecture Search for Game Theoretic Deep Learning Models](https://mlsanity.com/paper/2410.04764/) (2024)

## Abstract (arXiv)

Generative adversarial networks (GANs) represent a zero-sum game between two machine players, a generator and a discriminator, designed to learn the distribution of data. While GANs have achieved state-of-the-art performance in several benchmark learning tasks, GAN minimax optimization still poses great theoretical and empirical challenges. GANs trained using first-order optimization methods commonly fail to converge to a stable solution where the players cannot improve their objective, i.e., the Nash equilibrium of the underlying game. Such issues raise the question of the existence of Nash equilibrium solutions in the GAN zero-sum game. In this work, we show through several theoretical and numerical results that indeed GAN zero-sum games may not have any local Nash equilibria. To characterize an equilibrium notion applicable to GANs, we consider the equilibrium of a new zero-sum game with an objective function given by a proximal operator applied to the original objective, a solution we call the proximal equilibrium. Unlike the Nash equilibrium, the proximal equilibrium captures the sequential nature of GANs, in which the generator moves first followed by the discriminator. We prove that the optimal generative model in Wasserstein GAN problems provides a proximal equilibrium. Inspired by these results, we propose a new approach, which we call proximal training, for solving GAN problems. We discuss several numerical experiments demonstrating the existence of proximal equilibrium solutions in GAN minimax problems.