BriefGPT.xyz
Apr, 2023
在Bures-Wasserstein空间中通过JKO实现前向后向的高斯变分推断
Forward-backward Gaussian variational inference via JKO in the Bures-Wasserstein Space
HTML
PDF
Michael Diao, Krishnakumar Balasubramanian, Sinho Chewi, Adil Salim
TL;DR
本文提出了正向反向高斯变分推断算法，利用KL散度的结构，能够有效逼近高斯目标分布，得到了最新颖的收敛保证。
Abstract
variational inference
(VI) seeks to approximate a target distribution $\pi$ by an element of a tractable family of distributions. Of key interest in statistics and machine learning is
gaussian vi
, which approxima
→