DeepAI AI Chat
Log In Sign Up

Metropolis-Hastings Generative Adversarial Networks

by   Ryan Turner, et al.

We introduce the Metropolis-Hastings generative adversarial network (MH-GAN), which combines aspects of Markov chain Monte Carlo and GANs. The MH-GAN draws samples from the distribution implicitly defined by a GAN's discriminator-generator pair, as opposed to sampling in a standard GAN which draws samples from the distribution defined by the generator. It uses the discriminator from GAN training to build a wrapper around the generator for improved sampling. With a perfect discriminator, this wrapped generator samples from the true distribution on the data exactly even when the generator is imperfect. We demonstrate the benefits of the improved generator on multiple benchmark datasets, including CIFAR-10 and CelebA, using DCGAN and WGAN.


page 8

page 9


Collaborative GAN Sampling

Generative adversarial networks (GANs) have shown great promise in gener...

Dihedral angle prediction using generative adversarial networks

Several dihedral angles prediction methods were developed for protein st...

Boundary-Seeking Generative Adversarial Networks

We introduce a novel approach to training generative adversarial network...

MCL-GAN: Generative Adversarial Networks with Multiple Specialized Discriminators

We propose a generative adversarial network with multiple discriminators...

A Study into the similarity in generator and discriminator in GAN architecture

One popular generative model that has high-quality results is the Genera...

Unbalanced GANs: Pre-training the Generator of Generative Adversarial Network using Variational Autoencoder

We propose Unbalanced GANs, which pre-trains the generator of the genera...

Generalization and Equilibrium in Generative Adversarial Nets (GANs)

We show that training of generative adversarial network (GAN) may not ha...

Code Repositories


Metropolis-Hastings GAN in Tensorflow for enhanced generator sampling

view repo


Experiments on Metropolis-Hastings Generative Adversarial Networks, including my own implementation

view repo