Metropolis-Hastings Generative Adversarial Networks

4 code implementations • 28 Nov 2018 • Ryan Turner, Jane Hung, Eric Frank, Yunus Saatci, Jason Yosinski

We introduce the Metropolis-Hastings generative adversarial network (MH-GAN), which combines aspects of Markov chain Monte Carlo and GANs.

Generative Adversarial Network

Bayesian GAN

1 code implementation • NeurIPS 2017 • Yunus Saatci, Andrew G. Wilson

Generative adversarial networks (GANs) can implicitly learn rich distributions over images, audio, and data which are hard to model with an explicit likelihood.