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

02/17/2021
by   Aye Phyu Phyu Aung, et al.
8

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.

READ FULL TEXT

page 7

page 15

page 16

page 17

page 18

page 19

page 22

research
02/21/2020

GANs May Have No Nash Equilibria

Generative adversarial networks (GANs) represent a zero-sum game between...
research
10/17/2020

Training Generative Adversarial Networks via stochastic Nash games

Generative adversarial networks (GANs) are a class of generative models ...
research
02/28/2023

Double Dynamic Sparse Training for GANs

The past decade has witnessed a drastic increase in modern deep neural n...
research
12/02/2017

GANGs: Generative Adversarial Network Games

Generative Adversarial Networks (GAN) have become one of the most succes...
research
05/08/2017

Geometric GAN

Generative Adversarial Nets (GANs) represent an important milestone for ...
research
06/11/2019

A Closer Look at the Optimization Landscapes of Generative Adversarial Networks

Generative adversarial networks have been very successful in generative ...
research
04/07/2023

Correcting Model Misspecification via Generative Adversarial Networks

Machine learning models are often misspecified in the likelihood, which ...

Please sign up or login with your details

Forgot password? Click here to reset