On the regularization of Wasserstein GANs

  title={On the regularization of Wasserstein GANs},
  author={Henning Petzka and Asja Fischer and Denis Lukovnicov},
Since their invention, generative adversarial networks (GANs) have become a popular approach for learning to model a distribution of real (unlabeled) data. Convergence problems during training are overcome by Wasserstein GANs which minimize the distance between the model and the empirical distribution in terms of a different metric, but thereby introduce a Lipschitz constraint into the optimization problem. A simple way to enforce the Lipschitz constraint on the class of functions, which can be… CONTINUE READING
Highly Cited
This paper has 18 citations. REVIEW CITATIONS
Related Discussions
This paper has been referenced on Twitter 27 times. VIEW TWEETS

From This Paper

Topics from this paper.


Publications referenced by this paper.
Showing 1-10 of 21 references

Optimal Transport: Old and New

Cédric Villani
Grundlehren der mathematischen Wissenschaften. Springer Berlin Heidelberg, • 2008
View 5 Excerpts
Highly Influenced

Generative Adversarial Nets

View 4 Excerpts
Highly Influenced

Improved Techniques for Training GANs

NIPS • 2016
View 6 Excerpts
Highly Influenced

2017) point out, it does not matter whether to maximize over 1-Lipschitz or αLipschitz continuous functions, since we can equivalently optimize α ·W (μ, ν) instead of W (μ, ν)


Similar Papers

Loading similar papers…