mlsanityData to 7 Oct 2026

Fully Bayesian Autoencoders with Latent Sparse Gaussian Processes

arXiv 2302.04534 ↗First posted 9 Feb 2023cs.LG stat.MLcited by 9

Not on the map. Why?

Abstract (arXiv)

Autoencoders and their variants are among the most widely used models in representation learning and generative modeling. However, autoencoder-based models usually assume that the learned representations are i.i.d. and fail to capture the correlations between the data samples. To address this issue, we propose a novel Sparse Gaussian Process Bayesian Autoencoder (SGPBAE) model in which we impose fully Bayesian sparse Gaussian Process priors on the latent space of a Bayesian Autoencoder. We perform posterior estimation for this model via stochastic gradient Hamiltonian Monte Carlo. We evaluate our approach qualitatively and quantitatively on a wide range of representation learning and generative modeling tasks and show that our approach consistently outperforms multiple alternatives relying on Variational Autoencoders.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 42 of its 75 references that are in the map. First posted on arXiv 9 Feb 2023.

Builds on

42 of 75 references.

References · 42

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2015Variational Inference with Normalizing Flowscited by 2,161
  4. 2020Bayesian Deep Learning and a Probabilistic Perspective of Generalizationcited by 480
  5. 2013Gaussian Processes for Big Datacited by 377
  6. 2014Stochastic Gradient Hamiltonian Monte Carlocited by 341
  7. 2018Neural Processescited by 307
  8. 2021What Are Bayesian Neural Network Posteriors Really Like?cited by 307
  9. 2017VAE with a VampPriorcited by 247
  10. 2017Advances in Variational Inferencecited by 236
  11. 2014Scalable Variational Gaussian Process Classificationcited by 226
  12. 2016Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoderscited by 219
30 more
  1. 2019Cyclical Stochastic Gradient MCMC for Bayesian Deep Learningcited by 203
  2. 2016Variational Lossy Autoencodercited by 175
  3. 2019GP-VAE: Deep Probabilistic Time Series Imputationcited by 171
  4. 2017Doubly Stochastic Variational Inference for Deep Gaussian Processescited by 143
  5. 2018Inference Suboptimality in Variational Autoencoderscited by 131
  6. 2018Iterative Amortized Inferencecited by 93
  7. 2022An Introduction to Neural Data Compressioncited by 78
  8. 2018Gaussian Process Prior Variational Autoencoderscited by 72
  9. 2020All You Need is a Good Functional Prior for Bayesian Deep Learningcited by 61
  10. 2018Resampled Priors for Variational Autoencoderscited by 56
  11. 2015Bayesian Dark Knowledgecited by 45
  12. 2015MCMC for Variationally Sparse Gaussian Processescited by 44
  13. 2016Stick-Breaking Variational Autoencoderscited by 44
  14. 2019Bayesian Variational Autoencoders for Unsupervised Out-of-Distribution Detectioncited by 35
  15. 2018Adversarial Distillation of Bayesian Neural Network Posteriorscited by 27
  16. 2017Learning to Draw Samples with Amortized Stein Variational Gradient Descentcited by 26
  17. 2020Longitudinal Variational Autoencodercited by 25
  18. 2017Approximate Inference with Amortised MCMCcited by 22
  19. 2016Learning to Draw Samples: With Application to Amortized MLE for Generative Adversarial Learningcited by 21
  20. 2017On the challenges of learning with inference networks on sparse, high-dimensional datacited by 21
  21. 2020Sparse Gaussian Process Variational Autoencoderscited by 21
  22. 2020Scalable Gaussian Process Variational Autoencoderscited by 20
  23. 2022Markovian Gaussian Process Variational Autoencoderscited by 16
  24. 2018The Gaussian Process Autoregressive Regression Model (GPAR)cited by 12
  25. 2021Model Selection for Bayesian Autoencoderscited by 10
  26. 2022Laplacian Autoencoders for Learning Stochastic Representationscited by 10
  27. 2019Scalable Training of Inference Networks for Gaussian-Process Modelscited by 8
  28. 2016Generic Inference in Latent Gaussian Process Modelscited by 4
  29. 2022Sparse Gaussian Process Hyperparameters: Optimize or Integrate?cited by 4
  30. 2022Do Bayesian Variational Autoencoders Know What They Don't Know?cited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 2; 2025: 4; 2026: 1.

9 papers.

  1. 2025Generative Uncertainty in Diffusion Modelscited by 20
  2. 2023One-Line-of-Code Data Mollification Improves Optimization of Likelihood-based Generative Modelscited by 4
  3. 2023PPG-to-ECG Signal Translation for Continuous Atrial Fibrillation Detection via Attention-based Deep State-Space Modelingcited by 4
  4. 2024Preventing Model Collapse in Gaussian Process Latent Variable Modelscited by 3
  5. 2025Neighbour-Driven Gaussian Process Variational Autoencoders for Scalable Structured Latent Modellingcited by 3
  6. 2024Deep Latent Variable Modeling of Physiological Signalscited by 0
  7. 2025PIGPVAE: Physics-Informed Gaussian Process Variational Autoencoderscited by 0
  8. 2025Parameter Space Analysis through Guided Visual Interpolationscited by 0
  9. 2026Modeling Temporal scRNA-seq Data with Latent Gaussian Process and Optimal Transportcited by 0