mlsanityData to 7 Oct 2026

Revisiting Bayesian Autoencoders with MCMC

arXiv 2104.05915 ↗First posted 13 Apr 2021cs.LG cs.AI stat.APcited by 10

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 38 of its 107 references that are in the map. First posted on arXiv 13 Apr 2021.

Builds on

38 of 107 references.

References · 38

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2013Auto-Encoding Variational Bayescited by 3,980
  3. 2016Variational Graph Auto-Encoderscited by 1,373
  4. 2019An Introduction to Variational Autoencoderscited by 997
  5. 2015Importance Weighted Autoencoderscited by 454
  6. 2016Tutorial on Variational Autoencoderscited by 404
  7. 2017Wasserstein Auto-Encoderscited by 371
  8. 2016Ladder Variational Autoencoderscited by 315
  9. 2018Variational Autoencoders for Collaborative Filteringcited by 308
  10. 2017Grammar Variational Autoencodercited by 283
  11. 2018Generating 3D faces using Convolutional Mesh Autoencoderscited by 267
  12. 2015Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inferencecited by 159
26 more
  1. 2017Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networkscited by 107
  2. 2018Generative Probabilistic Novelty Detection with Adversarial Autoencoderscited by 99
  3. 2019GMNN: Graph Markov Neural Networkscited by 82
  4. 2016Medical image denoising using convolutional denoising autoencoderscited by 76
  5. 2020Scaling Hamiltonian Monte Carlo Inference for Bayesian Neural Networks with Symmetric Splittingcited by 54
  6. 2017Generalizing Hamiltonian Monte Carlo with Neural Networkscited by 52
  7. 2019Robust Anomaly Detection in Images using Adversarial Autoencoderscited by 38
  8. 2020Marginal likelihood computation for model selection and hypothesis testing: an extensive reviewcited by 33
  9. 2018Variational Recurrent Neural Machine Translationcited by 23
  10. 2017Denoising Adversarial Autoencoderscited by 20
  11. 2017Deep Learning: A Bayesian Perspectivecited by 20
  12. 2018Revisiting the Gelman-Rubin Diagnosticcited by 18
  13. 2016Robust LSTM-Autoencoders for Face De-Occlusion in the Wildcited by 17
  14. 2018Langevin-gradient parallel tempering for Bayesian neural learningcited by 14
  15. 2019Interpretable Embeddings From Molecular Simulations Using Gaussian Mixture Variational Autoencoderscited by 13
  16. 2016Maximum a Posteriori Estimators as a Limit of Bayes Estimatorscited by 12
  17. 2020Architectural Implications of Graph Neural Networkscited by 12
  18. 2017Autoencoder with recurrent neural networks for video forgery detectioncited by 10
  19. 2019Temporal Neighbourhood Aggregation: Predicting Future Links in Temporal Graphs via Recurrent Variational Graph Convolutionscited by 8
  20. 2018AEkNN: An AutoEncoder kNN-based classifier with built-in dimensionality reductioncited by 5
  21. 2018Multi-core parallel tempering Bayeslands for basin and landscape evolutioncited by 5
  22. 2018Adversarial Auto-encoders for Speech Based Emotion Recognitioncited by 4
  23. 2018Surrogate-assisted parallel tempering for Bayesian neural learningcited by 3
  24. 2020Nonlinear Dimensionality Reduction for Data Visualization: An Unsupervised Fuzzy Rule-based Approachcited by 2
  25. 2013Ensembles of Classifiers based on Dimensionality Reductioncited by 1
  26. 2020Multi-Objective Evolutionary approach for the Performance Improvement of Learners using Ensembling Feature selection and Discretization Technique on Medical datacited by 1

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 2; 2023: 4; 2024: 2; 2025: 1.

10 papers.

  1. 2022Bayesian autoencoders for data-driven discovery of coordinates, governing equations and fundamental constantscited by 24
  2. 2023A review of ensemble learning and data augmentation models for class imbalanced problems: combination, implementation and evaluationcited by 24
  3. 2021SMOTified-GAN for class imbalanced pattern classification problemscited by 20
  4. 2023Multi-Modal Deep Learning for Credit Rating Prediction Using Text and Numerical Data Streamscited by 13
  5. 2023Bayesian neural networks via MCMC: a Python-based tutorialcited by 8
  6. 2022Bayesian autoencoders with uncertainty quantification: Towards trustworthy anomaly detectioncited by 4
  7. 2024Bayes-CATSI: A variational Bayesian deep learning framework for medical time series data imputationcited by 2
  8. 2024Uniform Transformation: Refining Latent Representation in Variational Autoencoderscited by 1
  9. 2023Latent Space Perspicacity and Interpretation Enhancement (LS-PIE) Frameworkcited by 0
  10. 2025Convolutional neural networks for mineral prospecting through alteration mapping with remote sensing datacited by 0