Revisiting Bayesian Autoencoders with MCMC

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.

References in corpus (21)

• Adam: A Method for Stochastic Optimization
• An Introduction to Variational Autoencoders
• Exchange Monte Carlo Method and Application to Spin Glass Simulations
• Tutorial on Variational Autoencoders
• Parallel Tempering Algorithm for Conformational Studies of Biological Molecules
• Variational Graph Auto-Encoders
• Medical image denoising using convolutional denoising autoencoders
• Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference
• Wasserstein Auto-Encoders
• GMNN: Graph Markov Neural Networks
• Generative Probabilistic Novelty Detection with Adversarial Autoencoders
• Deep Learning: A Bayesian Perspective
• Maximum a Posteriori Estimators as a Limit of Bayes Estimators
• Marginal likelihood computation for model selection and hypothesis testing: an extensive review
• Architectural Implications of Graph Neural Networks
• Bayesian graph convolutional neural networks via tempered MCMC
• Generalizing Hamiltonian Monte Carlo with Neural Networks
• Scaling Hamiltonian Monte Carlo Inference for Bayesian Neural Networks with Symmetric Splitting
• Nonlinear Dimensionality Reduction for Data Visualization: An Unsupervised Fuzzy Rule-based Approach
• Multi-core parallel tempering Bayeslands for basin and landscape evolution
• Multi-Objective Evolutionary approach for the Performance Improvement of Learners using Ensembling Feature selection and Discretization Technique on Medical data

Cited by in corpus (4)

• SMOTified-GAN for class imbalanced pattern classification problems
• COVID-19 sentiment analysis via deep learning during the rise of novel cases
• Bayesian neural networks via MCMC: a Python-based tutorial
• Multi-Modal Deep Learning for Credit Rating Prediction Using Text and Numerical Data Streams