Revisiting Bayesian Autoencoders With MCMC

Autoencoders gained popularity in the deep learning revolution given their ability to compress data and provide dimensionality reduction. Although prominent deep learning methods have been used to enhance autoencoders, the need to provide robust uncertainty quantification remains a challenge. This h...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access Vol. 10; pp. 40482 - 40495
Main Authors: Chandra, Rohitash, Jain, Mahir, Maharana, Manavendra, Krivitsky, Pavel N.
Format: Journal Article
Language:English
Published: Piscataway IEEE 2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
autoencoders
Bayes methods
Bayesian analysis
Bayesian deep learning
Computational modeling
Data models
Decoding
Deep learning
Langevin dynamics
Machine learning
Markov chains
MCMC
Neural networks
parallel tempering
Proposals
Sampling
Statistical inference
Uncertainty
ISSN:2169-3536, 2169-3536
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Autoencoders gained popularity in the deep learning revolution given their ability to compress data and provide dimensionality reduction. Although prominent deep learning methods have been used to enhance autoencoders, the need to provide robust uncertainty quantification remains a challenge. This has been addressed with variational autoencoders so far. Bayesian inference via Markov Chain Monte Carlo (MCMC) sampling has faced several limitations for large models; however, recent advances in parallel computing and advanced proposal schemes have opened routes less traveled. This paper presents Bayesian autoencoders powered by MCMC sampling implemented using parallel computing and Langevin-gradient proposal distribution. The results indicate that the proposed Bayesian autoencoder provides similar performance accuracy when compared to related methods in the literature. Furthermore, it provides uncertainty quantification in the reduced data representation. This motivates further applications of the Bayesian autoencoder framework for other deep learning models.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2022.3163270