BriefGPT.xyz
Jul, 2019
Copula＆边缘流：将边缘与其联合分离
Copula & Marginal Flows: Disentangling the Marginal from its Joint
HTML
PDF
Magnus Wiese, Robert Knobloch, Ralf Korn
TL;DR
本论文通过引入copula和marginal generative flows(CM流)，解决了深度生成网络中存在的尾部特性建模或外推的问题并提出了上界方法。最终的结果支持了CM流的使用。
Abstract
deep generative networks
such as
gans
and
normalizing flows
flourish in the context of high-dimensional tasks such as image generation. Ho
→