Need help with PresGANs?
Click the “chat” button below for chat support from the developer who created it, or find similar developers for support.

About the developer

136 Stars 17 Forks 5 Commits 1 Opened issues


Prescribed Generative Adversarial Networks

Services available


Need anything else?

Contributors list

# 34,450
1 commit
# 45,655
1 commit

Repository for Prescribed Generative Adversarial Networks at

Abstract: Generative adversarial networks (GANs) are a powerful approach to unsupervised learning. They have achieved state-of-the-art performance in the image domain. However, GANs are limited in two ways. They often learn distributions with low support—a phenomenon known as mode collapse—and they do not guarantee the existence of a probability density, which makes evaluating generalization using predictive log-likelihood impossible. In this paper, we develop the prescribed GAN (PresGAN) to address these shortcomings. PresGANs add noise to the output of a density network and optimize an entropy-regularized adversarial loss. The added noise renders tractable approximations of the predictive log-likelihood and stabilizes the training procedure. The entropy regularizer encourages PresGANs to capture all the modes of the data distribution. Fitting PresGANs involves computing the intractable gradients of the entropy regularization term; PresGANs sidestep this intractability using unbiased stochastic estimates. We evaluate PresGANs on several datasets and found they mitigate mode collapse and generate samples with high perceptual quality. We further found that PresGANs reduce the gap in performance in terms of predictive log-likelihood between traditional GANs and variational auto-encoders (VAEs).

This repository contains a

implementation for PresGANs.

These GANs have

  • High sample quality
  • High sample diversity
  • Tractable predictive log-likelihood

They use an entropy regularization term to overcome mode collapse, which is common with traditional GANs.

PresGAN loss

Example usage

$ python --dataset mnist --model presgan

To cite please use the following bibtex

  title={Prescribed Generative Adversarial Networks},
  author={Dieng, Adji B and Ruiz, Francisco JR and Blei, David M and Titsias, Michalis K},
  journal={arXiv preprint arXiv:1910.04302},

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.