Wasserstein Generative Adversarial Networks
Abstract
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.
Cite
Text
Arjovsky et al. "Wasserstein Generative Adversarial Networks." International Conference on Machine Learning, 2017.Markdown
[Arjovsky et al. "Wasserstein Generative Adversarial Networks." International Conference on Machine Learning, 2017.](https://mlanthology.org/icml/2017/arjovsky2017icml-wasserstein/)BibTeX
@inproceedings{arjovsky2017icml-wasserstein,
title = {{Wasserstein Generative Adversarial Networks}},
author = {Arjovsky, Martin and Chintala, Soumith and Bottou, Léon},
booktitle = {International Conference on Machine Learning},
year = {2017},
pages = {214-223},
volume = {70},
url = {https://mlanthology.org/icml/2017/arjovsky2017icml-wasserstein/}
}