论文标题
F-Diverences和F-GAN培训的特性
Properties of f-divergences and f-GAN training
论文作者
论文摘要
在这份技术报告中，我们描述了F-Diverence和F-GAN培训的一些属性。我们提出了F-Divergence下限的基本推导，这构成了F-GAN训练的基础。我们获得了F-Diverences和F-GAN培训的内容丰富但也许不足的特性，包括梯度匹配的属性以及所有F-Diverences都同意附近分布之间差异的总体规模因素。我们提供详细的表达式，用于计算各种常见的F差异及其变异下限。最后，根据我们的重新制定，我们以一种可以提高其稳定性的方式稍微概括了F-GAN培训。
In this technical report we describe some properties of f-divergences and f-GAN training. We present an elementary derivation of the f-divergence lower bounds which form the basis of f-GAN training. We derive informative but perhaps underappreciated properties of f-divergences and f-GAN training, including a gradient matching property and the fact that all f-divergences agree up to an overall scale factor on the divergence between nearby distributions. We provide detailed expressions for computing various common f-divergences and their variational lower bounds. Finally, based on our reformulation, we slightly generalize f-GAN training in a way that may improve its stability.
