BriefGPT.xyz
Jan, 2018
Gradient Layer: 增强生成模型对抗训练的收敛
Gradient Layer: Enhancing the Convergence of Adversarial Training for Generative Models
HTML
PDF
Atsushi Nitanda, Taiji Suzuki
TL;DR
本文提出了在生成对抗网络训练中,通过引入梯度层来寻找无限维空间中的下降方向,以克服深模型训练中局部最优问题,从而获得更快更好的收敛性能以及更强的表达能力。
Abstract
We propose a new technique that boosts the
convergence
of training
generative adversarial networks
. Generally, the rate of training
deep models
→