Wasserstein Generative Adversarial Networks, Martin Arjovsky, Soumith Chintala, and Léon Bottou, 2017Proceedings of the 34th International Conference on Machine Learning (ICML), Vol. 70 (Machine Learning Research)DOI: 10.5555/3305890.3306076 - 介绍了 Wasserstein GAN,阐述了其基于地球移动距离的理论基础,并提出了权重裁剪作为强制评论器Lipschitz约束的方法。
Improved Training of Wasserstein GANs, Ishaan Gulrajani, Faruk Ahmed, Martín Arjovsky, Vincent Dumoulin, and Aaron Courville, 2017Advances in Neural Information Processing Systems 30 (NeurIPS 2017) (Curran Associates, Inc.) - 针对WGAN中权重裁剪的局限性,提出了梯度惩罚,这是一种更有效、更稳定的正则化方法,用于强制执行Lipschitz约束。
Generative Adversarial Networks, Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, Yoshua Bengio, 2020Communications of the ACM, Vol. 63DOI: 10.1145/3422622 - 对生成对抗网络进行了综述,讨论了其动机、架构和训练挑战,包括WGAN等方法带来的稳定性改进需求。