02/02/2021

HiABP: Hierarchical Initialized ABP for Unsupervised Representation Learning

Jiankai Sun, Rui Liu, Bolei Zhou

Keywords:

Abstract Paper Similar Papers

Abstract: Although Markov chain Monte Carlo (MCMC) is useful for generating samples from the posterior distribution, it often suffers from intractability when dealing with large-scale datasets. To address this issue, we propose Hierarchical Initialized Alternating Back-propagation (HiABP) for efficient Bayesian inference. Especially, we endow Alternating Backpropagation (ABP) method with a well-designed initializer and hierarchical structure, composing the pipeline of Initializing, Improving, and Learning back-propagation. It saves much time for the generative model to initialize the latent variable by constraining a sampler to be close to the true posterior distribution. The initialized latent variable is then improved significantly by an MCMC sampler. Thus the proposed method has the strengths of both methods, i.e., the effectiveness of MCMC and the efficiency of variational inference. Experimental results validate our framework can outperform other popular deep generative models in modeling natural images and learning from incomplete data. We further demonstrate the unsupervised disentanglement of hierarchical latent representation with controllable image synthesis.

The video of this talk cannot be embedded. You can watch it here:
https://slideslive.com/38948032
(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
 14:43 
 0
 0
 0
 0
 4:52 
 0
 0
 0
 0
 5:09 
 0
 0
 0
 0
 3:04 
 0
 0
 0
 0
 14:05 
 0
 0
 0
 0
 11:33 
 0
 0
 0
 0
 11:28 
 0
 0
 0
 0
 11:53 
 0
 0
 0
 0
 3:21 
 0
 0
 0
 0
 2:56 
 0
 0
 0
 0
 15:04 
 0
 0
 0
 0
 11:00 
 0
 0
 0
 0
 14:03 
 0
 0
 0
 0
 11:43 
 0
 0
 0
 0
 3:24 
 0
 0
 0
 0
 3:23 
 0
 0
 0
 0
 5:44 
 0
 0
 0
 0
 10:58 
 0
 0
 0
 0
 5:40 
 0
 0
 0
 0
 15:33 
 0
 0
 0
 0
 3:23 
 0
 0
 0
 0
 10:52 
 0
 0
 0
 0
 15:57 
 0
 0
 0
 0
 3:27 
 0
 0
 0
 0
 14:54 
 0
 0
 0
 0
 5:09 
 0
 0
 0
 0
 4:59 
 0
 1
 0
 0
 15:01 
 0
 0
 0
 0
 13:37 
 0
 0
 0
 0
 15:34 
 0
 0
 0
 0
 3:24 
 0
 0
 0
 0
 3:10 
 0
 0
 0
 0
 3:19 
 0
 0
 0
 0
 8:21 
 0
 0
 0
 0
 2:48 
 0
 0
 0
 0
 2:59 
 0
 0
 0
 0
 14:40 
 0
 0
 0
 0
 4:54 
 0
 0
 0
 0
 16:56 
 0
 0
 0
 0
 1:00