BriefGPT.xyz
Jul, 2019
对抗性利普希茨正则化
Virtual Adversarial Lipschitz Regularization
HTML
PDF
Dávid Terjék
TL;DR
本研究提出了一种名为Adversarial Lipschitz Regularization的方法，其可行地利用了显式的Lipschitz惩罚，并在训练Wasserstein GANs时表现出与隐式惩罚相同的性能表现，凸显了Lipschitz 正则化和对抗性训练之间的重要联系。
Abstract
generative adversarial networks
(GANs) are one of the most popular approaches when it comes to training generative models, among which variants of
wasserstein gans
are considered superior to the standard GAN form
→