Revisiting Bayesian Autoencoders with MCMC

TL;DR

This paper introduces a Bayesian autoencoder framework utilizing MCMC sampling with parallel computing and Langevin-gradient proposals, enabling uncertainty quantification in data compression tasks, and demonstrating comparable accuracy to existing methods.

Contribution

It presents a novel Bayesian autoencoder approach using MCMC with advanced proposals and parallelization, addressing uncertainty quantification in autoencoders.

Findings

Provides uncertainty quantification in autoencoders

Achieves similar accuracy to existing methods

Utilizes parallel computing for efficient MCMC sampling

Abstract

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.