Semi-Amortized Variational Autoencoders
Name
kim18e.pdf
Description
Published version
Size
636.06 KB
Format
Unknown
Checksum (MD5)
f8c3c0e1adf660761089255011bf7505
Author(s)
Kim, Yoon
Wiseman, Sam
Miller, Andrew C.
Sontag, David
Rush, Alexander M.
Date Issued
2018
Journal
35th International Conference on Machine Learning, ICML 2018
Citation
Kim, Yoon, Wiseman, Sam, Miller, Andrew C., Sontag, David and Rush, Alexander M. 2018. "Semi-Amortized Variational Autoencoders." 35th International Conference on Machine Learning, ICML 2018, 6.
Version
Final published version
Abstract
© CURRAN-CONFERENCE. All rights reserved. Amortized variational inference (AVI) replaces instance-specific local inference with a global inference network. While AVI has enabled efficient training of deep generative models such as variational autoencoders (VAE), recent empirical work suggests that inference networks can produce suboptimal variational parameters. We propose a hybrid approach, to use AVI to initialize the variational parameters and run stochastic variational inference (SVI) to refine them. Crucially, the local SVI procedure is itself differentiable, so the inference network and generative model can be trained end-to-end with gradient-based optimization. This semi-amortized approach enables the use of rich generative models without experiencing the posterior-collapse phenomenon common in training VAEs for problems like text generation. Experiments show this approach outperforms strong autoregressive and variational baselines on standard text and image datasets.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Massachusetts Institute of Technology. Institute for Medical Engineering & Science
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
http://proceedings.mlr.press/v80/kim18e.html
