BriefGPT.xyz
Jun, 2022
基于评分引导的中间层优化: 逆问题中的快速 Langevin 混合
Score-Guided Intermediate Layer Optimization: Fast Langevin Mixing for Inverse Problem
HTML
PDF
Giannis Daras, Yuval Dagan, Alexandros G. Dimakis, Constantinos Daskalakis
TL;DR
通过Langevin算法，我们扩展了Hand和Voroninski的工作，从有效的反演到有效的后验采样，并在latens space架构的生成模型中提出了SGILO方法,在低测量范围内，取得了极大的改进。
Abstract
We prove fast mixing and characterize the stationary distribution of the
langevin algorithm
for inverting random weighted DNN generators. This result extends the work of Hand and Voroninski from efficient inversion to efficient
→