BriefGPT.xyz
Jun, 2017
梯度下降GAN优化局部稳定
Gradient descent GAN optimization is locally stable
HTML
PDF
Vaishnavh Nagarajan, J. Zico Kolter
TL;DR
本文分析了生成对抗网络(GANs)的优化问题,通过引入正则化方法提高训练速度和稳定性,并对经典GAN和Wasserstein GAN优化过程的局部渐近稳定性进行了研究。
Abstract
Despite their growing prominence, optimization in
generative adversarial networks
(GANs) is still a poorly-understood topic. In this paper, we analyze the "
gradient descent
" form of
→