Learning Energy-based Model with Flow-based Backbone by Neural Transport MCMC

Sountsov Pavel
Sountsov Pavel
Vasudevan Srinivas
Vasudevan Srinivas
被引用4|浏览38

摘要

Learning energy-based model (EBM) requires MCMC sampling of the learned model as the inner loop of the learning algorithm. However, MCMC sampling of EBM in data space is generally not mixing, because the energy function, which is usually parametrized by deep network, is highly multi-modal in the data space. This is a serious handicap fo...更多

代码

数据

ZH
24小时获取PDF
引用
您的评分 :
0

 

标签
评论