mlsanityData to 14 Oct 2026

Variational Laplace Autoencoders

arXiv 2211.17267 ↗First posted 30 Nov 2022cs.LGcited by 7

Not on the map. Why?

Abstract (arXiv)

Variational autoencoders employ an amortized inference model to approximate the posterior of latent variables. However, such amortized variational inference faces two challenges: (1) the limited posterior expressiveness of fully-factorized Gaussian assumption and (2) the amortization error of the inference model. We present a novel approach that addresses both challenges. First, we focus on ReLU networks with Gaussian output and illustrate their connection to probabilistic PCA. Building on this observation, we derive an iterative algorithm that finds the mode of the posterior and apply full-covariance Gaussian posterior approximation centered on the mode. Subsequently, we present a general framework named Variational Laplace Autoencoders (VLAEs) for training deep generative models. Based on the Laplace approximation of the latent variable posterior, VLAEs enhance the expressiveness of the posterior while reducing the amortization error. Empirical results on MNIST, Omniglot, Fashion-MNIST, SVHN and CIFAR10 show that the proposed approach significantly outperforms other recent amortized or iterative methods on the ReLU networks.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 23 of its 45 references that are in the map. First posted on arXiv 30 Nov 2022.

Builds on

23 of 45 references.

References · 23

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  3. 2013Auto-Encoding Variational Bayescited by 4,053
  4. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,611
  5. 2015Variational Inference with Normalizing Flowscited by 2,170
  6. 2016Improving Variational Inference with Inverse Autoregressive Flowcited by 640
  7. 2015Generating Sentences from a Continuous Spacecited by 612
  8. 2015Importance Weighted Autoencoderscited by 456
  9. 2014On the Number of Linear Regions of Deep Neural Networkscited by 381
  10. 2015A Recurrent Latent Variable Model for Sequential Datacited by 362
  11. 2015DRAW: A Recurrent Neural Network For Image Generationcited by 191
  12. 2013Maxout Networkscited by 187
11 more
  1. 2018Inference Suboptimality in Variational Autoencoderscited by 132
  2. 2018A Hierarchical Latent Vector Model for Learning Long-Term Structure in Musiccited by 131
  3. 2017Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networkscited by 107
  4. 2013On the number of response regions of deep feed forward networks with piece-wise linear activationscited by 94
  5. 2018Iterative Amortized Inferencecited by 94
  6. 2018Semi-Amortized Variational Autoencoderscited by 83
  7. 2016Auxiliary Deep Generative Modelscited by 72
  8. 2016PixelVAE: A Latent Variable Model for Natural Imagescited by 70
  9. 2016Improving Variational Auto-Encoders using Householder Flowcited by 42
  10. 2015The Variational Gaussian Processcited by 30
  11. 2017On the challenges of learning with inference networks on sparse, high-dimensional datacited by 21

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 1; 2025: 3; 2026: 1.

7 papers.

  1. 2023Curvature-Sensitive Predictive Coding with Approximate Laplace Monte Carlocited by 3
  2. 2025Generalization in VAE and Diffusion Models: A Unified Information-Theoretic Analysiscited by 3
  3. 2024An Efficient Difference-of-Convex Solver for Privacy Funnelcited by 2
  4. 2023Neural Network Characterization and Entropy Regulated Data Balancing through Principal Component Analysiscited by 1
  5. 2025Beyond Diagonal Covariance: Flexible Posterior VAEs via Free-Form Injective Flowscited by 1
  6. 2025Likelihood-Free Variational Autoencoderscited by 0
  7. 2026Metabolic cost of information processing in Poisson variational autoencoderscited by 0