Paulina Grnarova, Kfir Y. Levy, Aurelien Lucchi, Thomas Hofmann, Andreas Krause
TL;DR本研究提出了一种名为Chekhov GAN 1的训练方法,将GAN的训练问题视为在零和博弈中找到一种混合策略,结合在线学习的思想,理论和实践证明了该方法收敛于半浅GAN体系结构,提高了稳定性和性能。
Abstract
We consider the problem of training generative models with a generative adversarial network (GAN). Although GANs can accurately model complex distributions, they are known to be difficult to train due to instabilities caused by a difficult minimax optimization problem. In this paper, w