论文信息 - From GAN to WGAN

From GAN to WGAN

This paper explains the math behind a generative adversarial network (GAN) model and why it is hard to be trained. Wasserstein GAN is intended to improve GANs' training by adopting a smooth metric for measuring the distance between two probability distributions.

Lilian Weng | Lilian Weng

[1] Wojciech Zaremba,et al. Improved Techniques for Training GANs , 2016, NIPS.

[2] Léon Bottou,et al. Wasserstein GAN , 2017, ArXiv.

[3] Léon Bottou,et al. Towards Principled Methods for Training Generative Adversarial Networks , 2017, ICLR.

[4] Aaron C. Courville,et al. Improved Training of Wasserstein GANs , 2017, NIPS.

[5] Yoshua Bengio,et al. Generative Adversarial Nets , 2014, NIPS.

[6] Ferenc Huszar,et al. How (not) to Train your Generative Model: Scheduled Sampling, Likelihood, Adversary? , 2015, ArXiv.