26/08/2020

A Wasserstein Minimum Velocity Approach to Learning Unnormalized Models

Ziyu Wang, Shuyu Cheng, Li Yueru, Jun Zhu, Bo Zhang

Keywords:

Abstract Paper Similar Papers

Abstract: Score matching provides an effective approach to learning flexible unnormalized models, but its scalability is limited by the need to evaluate a second-order derivative. In this paper, we present a scalable approximation to a general family of learning objectives including score matching, by observing a new connection between these objectives and Wasserstein gradient flows. We present applications with promise in learning neural density estimators on manifolds, and training implicit variational and Wasserstein auto-encoders with a manifold-valued prior.

 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at AISTATS 2020 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment
no comments yet
code of conduct: tbd Characters remaining: 140

Similar Papers

 2
 1
 0
 0
 13:27 
 0
 0
 0
 0
 10:54 
 0
 0
 0
 0
 4:47 
 0
 0
 0
 0
 8:56 
 0
 0
 0
 0
 14:30 
 0
 0
 0
 0
 15:26 
 0
 0
 0
 0
 5:11 
 0
 0
 0
 0
 5:25 
 0
 0
 0
 1
 2:51 
 0
 0
 0
 0
 2:59 
 0
 0
 0
 0
 14:26 
 0
 0
 0
 0
 18:48 
 1
 0
 0
 0
 2:43 
 0
 0
 0
 0
 13:43 
 0
 0
 0
 0
 5:16 
 0
 0
 0
 0
 12:31 
 0
 0
 0
 0
 14:46 
 0
 0
 0
 0
 12:11 
 0
 0
 0
 0
 4:47 
 0
 0
 0
 0
 2:57 
 0
 0
 0
 0
 6:45 
 0
 0
 0
 0
 12:59 
 0
 0
 0
 0
 3:21 
 0
 0
 0
 0
 5:10 
 0
 0
 0
 0
 15:02 
 0
 0
 0
 0
 3:21 
 0
 0
 0
 0
 9:58 
 0
 0
 0
 0
 17:43 
 0
 0
 0
 0
 5:38 
 0
 0
 0
 0
 3:26 
 0
 0
 0
 0
 3:25 
 0
 0
 0
 0
 3:23 
 0
 0
 0
 0
 3:44 
 0
 0
 0
 0
 14:40 
 0
 0
 0
 0
 9:51 
 0
 0
 0
 0
 12:27 
 0
 0
 0
 0
 13:54 
 0
 0
 0
 0
 3:24 
 0
 0
 0
 0
 14:59 
 0
 0
 0
 0
 3:54