mlsanityData to 14 Oct 2026

Resampled Priors for Variational Autoencoders

arXiv 1810.11428 ↗First posted 26 Oct 2018stat.ML cs.LGcited by 57

Not on the map. Why?

Abstract (arXiv)

We propose Learned Accept/Reject Sampling (LARS), a method for constructing richer priors using rejection sampling with a learned acceptance function. This work is motivated by recent analyses of the VAE objective, which pointed out that commonly used simple priors can lead to underfitting. As the distribution induced by LARS involves an intractable normalizing constant, we show how to estimate it and its gradients efficiently. We demonstrate that LARS priors improve VAE performance on several standard datasets both when they are learned jointly with the rest of the model and when they are fitted to a pretrained model. Finally, we show that LARS can be combined with existing methods for defining flexible priors for an additional boost in performance.

Key facts. Cited by 57 papers in the map (data through 14 Oct 2026). First posted on arXiv 26 Oct 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 16; 2022: 17; 2023: 10; 2024: 5; 2025: 7; 2026: 2.

57 papers.

Sort:

By area:

  1. 2021Score-based Generative Modeling in Latent Spacecited by 636
  2. 2022LION: Latent Point Diffusion Models for 3D Shape Generationcited by 553
  3. 2021Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Modelscited by 252
  4. 2022DiffuseVAE: Efficient, Controllable and High-Fidelity Generation from Low-Dimensional Latentscited by 104
  5. 2021Priors in Bayesian Deep Learning: A Reviewcited by 101
  6. 2022Refining Generative Process with Discriminator Guidance in Score-based Diffusion Modelscited by 100
  7. 2021Resampling Base Distributions of Normalizing Flowscited by 42
  8. 2022VAEL: Bridging Variational Autoencoders and Probabilistic Logic Programmingcited by 31
  9. 2022Universal approximation property of invertible neural networkscited by 30
  10. 2021Data Augmentation in High Dimensional Low Sample Size Setting Using a Geometry-Based Variational Autoencodercited by 27
  11. 2022Particle algorithms for maximum likelihood training of latent variable modelscited by 26
  12. 2022Pythae: Unifying Generative Autoencoders in Python -- A Benchmarking Use Casecited by 26
38 more
  1. 2024You Only Sample Once: Taming One-Step Text-to-Image Synthesis by Self-Cooperative Diffusion GANscited by 26
  2. 2022A Geometric Perspective on Variational Autoencoderscited by 24
  3. 2021A survey on Variational Autoencoders from a GreenAI perspectivecited by 22
  4. 2021Regularising Inverse Problems with Generative Machine Learning Modelscited by 22
  5. 2023Learning Manifold Dimensions with Conditional Variational Autoencoderscited by 20
  6. 2022Adaptive Multi-stage Density Ratio Estimation for Learning Latent Space Energy-based Modelcited by 18
  7. 2021Local Disentanglement in Variational Auto-Encoders Using Jacobian L1 Regularizationcited by 17
  8. 2023The Sample Complexity of Approximate Rejection Sampling with Applications to Smoothed Online Learningcited by 13
  9. 2022Multiple Importance Sampling ELBO and Deep Ensembles of Variational Approximationscited by 12
  10. 2022Bottlenecks CLUB: Unifying Information-Theoretic Trade-offs Among Complexity, Leakage, and Utilitycited by 12
  11. 2022Comparing the latent space of generative modelscited by 12
  12. 2021A prior-based approximate latent Riemannian metriccited by 11
  13. 2021On Incorporating Inductive Biases into VAEscited by 11
  14. 2021Model Selection for Bayesian Autoencoderscited by 10
  15. 2023Fully Bayesian Autoencoders with Latent Sparse Gaussian Processescited by 9
  16. 2024Monotone, Bi-Lipschitz, and Polyak-Lojasiewicz Networkscited by 9
  17. 2021Distantly Supervised Relation Extraction with Sentence Reconstruction and Knowledge Base Priorscited by 8
  18. 2024Hierarchical VAE with a Diffusion-based VampPriorcited by 8
  19. 2023Diffusion Models with Deterministic Normalizing Flow Priorscited by 7
  20. 2023Topology-Matching Normalizing Flows for Out-of-Distribution Detection in Robot Learningcited by 7
  21. 2024Counterfactual Concept Bottleneck Modelscited by 7
  22. 2021Variational Leakage: The Role of Information Complexity in Privacy Leakagecited by 6
  23. 2022Variational Sparse Coding with Learned Thresholdingcited by 6
  24. 2022Cooperation in the Latent Space: The Benefits of Adding Mixture Components in Variational Autoencoderscited by 6
  25. 2022Latent Space Diffusion Models of Cryo-EM Structurescited by 6
  26. 2023Matching aggregate posteriors in the variational autoencodercited by 6
  27. 2024Learning Latent Space Hierarchical EBM Diffusion Modelscited by 6
  28. 2025Distribution Matching Variational AutoEncodercited by 6
  29. 2023Deep Probabilistic Movement Primitives with a Bayesian Aggregatorcited by 4
  30. 2022Improving Variational Autoencoders with Density Gap-based Regularizationcited by 3
  31. 2021ByPE-VAE: Bayesian Pseudocoresets Exemplar VAEcited by 2
  32. 2023Unscented Autoencodercited by 2
  33. 2023On the Approximation of Bi-Lipschitz Maps by Invertible Neural Networkscited by 2
  34. 2023Reparameterized Variational Rejection Samplingcited by 2
  35. 2025Learning Energy-based Variational Latent Prior for VAEscited by 2
  36. 2021Momentum Contrastive Autoencoder: Using Contrastive Learning for Latent Space Distribution Matching in WAEcited by 1
  37. 2022Local Distance Preserving Auto-encoders using Continuous k-Nearest Neighbours Graphscited by 1
  38. 2025Studying Classifier(-Free) Guidance From a Classifier-Centric Perspectivecited by 1

50 most cited of 57 All 57 (JSON)