Revisiting Bayesian Autoencoders with MCMC
This is an incremental improvement for researchers needing uncertainty quantification in autoencoders, as it adapts existing MCMC techniques to a specific deep learning model.
The paper tackles the challenge of robust uncertainty quantification in autoencoders by proposing a Bayesian autoencoder using MCMC sampling with parallel computing and Langevin-gradient proposals, achieving similar performance accuracy to existing methods while providing uncertainty in the reduced representation.
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.