BriefGPT.xyz
Jan, 2017
AdaGAN：提升生成式模型
AdaGAN: Boosting Generative Models
HTML
PDF
Ilya Tolstikhin, Sylvain Gelly, Olivier Bousquet, Carl-Johann Simon-Gabriel, Bernhard Schölkopf
TL;DR
该研究使用增量算法AdaGAN训练Generative Adversarial Networks（GAN）来解决GAN模型中出现的missing modes问题，并且证明了当每一步是最优的时候，这种增量方法可以在有限步数内收敛到真实分布，否则以指数速度收敛。
Abstract
generative adversarial networks
(
gan
) (Goodfellow et al., 2014) are an effective method for training generative models of complex data such as natural images. However, they are notoriously hard to train and can s
→