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 methods have been used enhance autoencoders, need robust uncertainty quantification remains a challenge. This has addressed with variational autoencoders so far. Bayesian inference via Markov Chain Monte Carlo (MCMC) sampling faced several limitations for large models; however, recent advances parallel computing advanced proposal schemes opened routes less traveled. paper presents powered by MCMC implemented using Langevin-gradient distribution. The results indicate that proposed autoencoder provides similar performance accuracy when compared related literature. Furthermore, it reduced representation. motivates further applications of framework other models.