02/02/2021

Improving Generative Moment Matching Networks with Distribution Partition

Yong Ren, Yucen Luo, Jun Zhu

Keywords:

Abstract Paper Similar Papers

Abstract: Generative moment matching networks (GMMN) present a theoretically sound approach to learning deep generative mod-els. However, such methods are typically limited by the high sample complexity, thereby impractical in generating complex data. In this paper, we present a new strategy to train GMMN with a low sample complexity while retaining the theoretical soundness. Our method introduces some auxiliary variables, whose values are provided by a pre-trained model such as an encoder network in practice. Conditioned on these variables, we partition the distribution into a set of conditional distributions, which can be effectively matched with a low sample complexity. We instantiate this strategy by presenting an amortized network called GMMN-DP with shared auxiliary variable information for the data generation task, as well as developing an efficient stochastic training algorithm.The experimental results show that GMMN-DP can generate complex samples on datasets such as CelebA and CIFAR-10, where the vanilla GMMN fails.

The video of this talk cannot be embedded. You can watch it here:
https://slideslive.com/38948066
(Link will open in new window)
 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at AAAI 2021 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

 0
 0
 0
 0
 3:19 
 0
 0
 0
 0
 13:54 
 1
 0
 0
 1
 5:03 
 0
 0
 0
 0
 5:06 
 0
 0
 0
 0
 5:07 
 0
 0
 0
 0
 11:40 
 0
 0
 0
 0
 11:26 
 0
 0
 0
 0
 14:26 
 0
 0
 0
 0
 13:31 
 0
 0
 0
 0
 14:51 
 0
 0
 0
 0
 5:22 
 0
 0
 0
 0
 4:51 
 0
 0
 0
 1
 5:54 
 0
 0
 0
 0
 10:41 
 0
 0
 0
 0
 3:19 
 0
 0
 0
 0
 13:29 
 0
 0
 0
 0
 5:01 
 0
 0
 0
 0
 11:27 
 0
 0
 0
 0
 6:56 
 0
 0
 0
 0
 16:27 
 0
 0
 0
 0
 6:15 
 0
 0
 0
 0
 13:50 
 0
 0
 0
 0
 14:16 
 0
 0
 0
 0
 13:34 
 0
 0
 0
 0
 5:17 
 0
 0
 0
 0
 15:34 
 0
 0
 0
 0
 12:26 
 0
 0
 0
 0
 15:15 
 0
 0
 0
 0
 19:57 
 0
 0
 0
 0
 6:01 
 0
 0
 0
 0
 3:04 
 0
 0
 0
 0
 9:24 
 0
 0
 0
 0
 11:48 
 0
 0
 0
 0
 19:29 
 0
 0
 0
 0
 11:11 
 0
 0
 0
 0
 11:24 
 0
 0
 0
 0
 14:08 
 0
 0
 0
 1
 12:45 
 0
 0
 0
 0
 4:34 
 0
 0
 0
 0
 12:36