BriefGPT.xyz
Jun, 2019
混合指数族近似下的快速简单的自然梯度变分推断
Fast and Simple Natural-Gradient Variational Inference with Mixture of Exponential-family Approximations
HTML
PDF
Wu Lin, Mohammad Emtiyaz Khan, Mark Schmidt
TL;DR
本论文使用自然梯度方法扩展到结构化逼近，并得到了简单的方程。与黑箱渐变方法相比，实验结果表明我们的自然渐变方法收敛更快，从而扩展了贝叶斯推断的应用范围。
Abstract
natural-gradient methods
enable fast and simple algorithms for
variational inference
, but due to computational difficulties, their use is mostly limited to \emph{minimal}
→