Wasserstein Generative Adversarial Networks

@inproceedings{Arjovsky2017WassersteinGA,
  title={Wasserstein Generative Adversarial Networks},
  author={Mart{\'i}n Arjovsky and Soumith Chintala and L{\'e}on Bottou},
  booktitle={ICML},
  year={2017}
}
We introduce a new algorithm named WGAN, an alternative to traditional GAN training. In this new model, we show that we can improve the stability of learning, get rid of problems like mode collapse, and provide meaningful learning curves useful for debugging and hyperparameter searches. Furthermore, we show that the corresponding optimization problem is sound, and provide extensive theoretical work highlighting the deep connections to different distances between distributions. 
Highly Influential
This paper has highly influenced 110 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 422 citations. REVIEW CITATIONS

Citations

Publications citing this paper.

423 Citations

0200400201720182019
Citations per Year
Semantic Scholar estimates that this publication has 423 citations based on the available data.

See our FAQ for additional information.

Similar Papers

Loading similar papers…