# DO-GAN: A Double Oracle Framework for Generative Adversarial Networks

arXiv: https://arxiv.org/abs/2102.08577 · HTML: https://mlsanity.com/paper/2102.08577/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 40 references that are in the map.
- First posted on arXiv 17 Feb 2021.

## Builds on (most cited first, 21 of 21)

- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Spectral Normalization for Generative Adversarial Networks](https://mlsanity.com/paper/1802.05957/) (2018)
- [Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning](https://mlsanity.com/paper/1704.03976/) (2017)
- [Generative Adversarial Text to Image Synthesis](https://mlsanity.com/paper/1605.05396/) (2016)
- [Unsupervised Image-to-Image Translation Networks](https://mlsanity.com/paper/1703.00848/) (2017)
- [A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning](https://mlsanity.com/paper/1711.00832/) (2017)
- [Unrolled Generative Adversarial Networks](https://mlsanity.com/paper/1611.02163/) (2016)
- [Generalization and Equilibrium in Generative Adversarial Nets (GANs)](https://mlsanity.com/paper/1703.00573/) (2017)
- [Variational Autoencoder for Deep Learning of Images, Labels and Captions](https://mlsanity.com/paper/1609.08976/) (2016)
- [Few-shot Image Generation with Elastic Weight Consolidation](https://mlsanity.com/paper/2012.02780/) (2020)
- [The Numerics of GANs](https://mlsanity.com/paper/1705.10461/) (2017)
- [Generative Multi-Adversarial Networks](https://mlsanity.com/paper/1611.01673/) (2016)
- [A Generalized Training Approach for Multiagent Learning](https://mlsanity.com/paper/1909.12823/) (2019)
- [Continual Learning in Generative Adversarial Nets](https://mlsanity.com/paper/1705.08395/) (2017)
- [Finding Mixed Nash Equilibria of Generative Adversarial Networks](https://mlsanity.com/paper/1811.02002/) (2018)
- [Stacked Generative Adversarial Networks](https://mlsanity.com/paper/1612.04357/) (2016)
- [GANs May Have No Nash Equilibria](https://mlsanity.com/paper/2002.09124/) (2020)

## Built on by (most cited first, 6 of 6)

- [Policy Space Response Oracles: A Survey](https://mlsanity.com/paper/2403.02227/) (2024)
- [Transferable Reward Learning by Dynamics-Agnostic Discriminator Ensemble](https://mlsanity.com/paper/2206.00238/) (2022)
- [X-GAN: A Generative AI-Powered Unsupervised Model for Main Vessel Segmentation of Glaucoma Screening](https://mlsanity.com/paper/2503.06743/) (2025)
- [A Game-Theoretic Perspective of Generalization in Reinforcement Learning](https://mlsanity.com/paper/2208.03650/) (2022)
- [Unified Policy Optimization for Continuous-action Reinforcement Learning in Non-stationary Tasks and Games](https://mlsanity.com/paper/2208.09452/) (2022)
- [Double Oracle Neural Architecture Search for Game Theoretic Deep Learning Models](https://mlsanity.com/paper/2410.04764/) (2024)

## Abstract (arXiv)

In this paper, we propose a new approach to train Generative Adversarial Networks (GANs) where we deploy a double-oracle framework using the generator and discriminator oracles. GAN is essentially a two-player zero-sum game between the generator and the discriminator. Training GANs is challenging as a pure Nash equilibrium may not exist and even finding the mixed Nash equilibrium is difficult as GANs have a large-scale strategy space. In DO-GAN, we extend the double oracle framework to GANs. We first generalize the players' strategies as the trained models of generator and discriminator from the best response oracles. We then compute the meta-strategies using a linear program. For scalability of the framework where multiple generators and discriminator best responses are stored in the memory, we propose two solutions: 1) pruning the weakly-dominated players' strategies to keep the oracles from becoming intractable; 2) applying continual learning to retain the previous knowledge of the networks. We apply our framework to established GAN architectures such as vanilla GAN, Deep Convolutional GAN, Spectral Normalization GAN and Stacked GAN. Finally, we conduct experiments on MNIST, CIFAR-10 and CelebA datasets and show that DO-GAN variants have significant improvements in both subjective qualitative evaluation and quantitative metrics, compared with their respective GAN architectures.