mlsanityData to 7 Oct 2026

Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks

arXiv 1701.04722 ↗First posted 17 Jan 2017cs.LGcited by 107

Not on the map. Why?

Abstract (arXiv)

Variational Autoencoders (VAEs) are expressive latent variable models that can be used to learn complex probability distributions from training data. However, the quality of the resulting model crucially relies on the expressiveness of the inference model. We introduce Adversarial Variational Bayes (AVB), a technique for training Variational Autoencoders with arbitrarily expressive inference models. We achieve this by introducing an auxiliary discriminative network that allows to rephrase the maximum-likelihood-problem as a two-player game, hence establishing a principled connection between VAEs and Generative Adversarial Networks (GANs). We show that in the nonparametric limit our method yields an exact maximum-likelihood assignment for the parameters of the generative model, as well as the exact posterior distribution over the latent variables given an observation. Contrary to competing approaches which combine VAEs with GANs, our approach has a clear theoretical justification, retains most advantages of standard Variational Autoencoders and is easy to implement.

Key facts. Cited by 107 papers in the map (data through 7 Oct 2026). First posted on arXiv 17 Jan 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2018: 1; 2019: 0; 2020: 2; 2021: 30; 2022: 21; 2023: 24; 2024: 10; 2025: 13; 2026: 6.

107 papers.

Sort:

By area:

  1. 2022Generative Adversarial Networkscited by 5,603
  2. 2021Self-Supervised Pretraining of 3D Features on any Point-Cloudcited by 217
  3. 2018Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flowcited by 103
  4. 2022Synthesizing Informative Training Samples with GANcited by 77
  5. 2021Posterior Meta-Replay for Continual Learningcited by 45
  6. 2021KALE Flow: A Relaxed KL Gradient Flow for Probabilities with Disjoint Supportcited by 37
  7. 2022GATSBI: Generative Adversarial Training for Simulation-Based Inferencecited by 36
  8. 2024A survey of synthetic data augmentation methods in computer visioncited by 34
  9. 2023A Rigorous Link between Deep Ensembles and (Variational) Bayesian Methodscited by 31
  10. 2021Adversarial and Contrastive Variational Autoencoder for Sequential Recommendationcited by 28
  11. 2022Diagnosing and Fixing Manifold Overfitting in Deep Generative Modelscited by 28
  12. 2022CaloMan: Fast generation of calorimeter showers with density estimation on learned manifoldscited by 28
38 more
  1. 2021DP-Image: Differential Privacy for Image Data in Feature Spacecited by 23
  2. 2023Denoising diffusion algorithm for inverse design of microstructures with fine-tuned nonlinear material propertiescited by 23
  3. 2023Spatiotemporal Self-supervised Learning for Point Clouds in the Wildcited by 23
  4. 2021Factor Analysis, Probabilistic Principal Component Analysis, Variational Inference, and Variational Autoencoder: Tutorial and Surveycited by 21
  5. 2020Biased Mixtures Of Experts: Enabling Computer Vision Inference Under Data Transfer Limitationscited by 20
  6. 2021Efficient Out-of-Distribution Detection Using Latent Space of β-VAE for Cyber-Physical Systemscited by 19
  7. 2021Stochastic Physics-Informed Neural Ordinary Differential Equationscited by 19
  8. 2023Semi-Implicit Variational Inference via Score Matchingcited by 19
  9. 2021Variational inference with a quantum computercited by 18
  10. 2021Lifelong Teacher-Student Network Learningcited by 18
  11. 2023Learning to Estimate 6DoF Pose from Limited Data: A Few-Shot, Generalizable Approach using RGB Imagescited by 18
  12. 2022Sliced Wasserstein Variational Inferencecited by 17
  13. 2024Sparse Inducing Points in Deep Gaussian Processes: Enhancing Modeling with Denoising Diffusion Variational Inferencecited by 16
  14. 2021Mind the Gap when Conditioning Amortised Inference in Sequential Latent-Variable Modelscited by 14
  15. 2023Hierarchical Semi-Implicit Variational Inference with Application to Diffusion Model Accelerationcited by 14
  16. 2025Generative Models in Decision Making: A Surveycited by 14
  17. 2021Function-space Inference with Sparse Implicit Processescited by 13
  18. 2023Uncertainty-Aware Pedestrian Trajectory Prediction via Distributional Diffusioncited by 13
  19. 2022Bottlenecks CLUB: Unifying Information-Theoretic Trade-offs Among Complexity, Leakage, and Utilitycited by 12
  20. 2023UMat: Uncertainty-Aware Single Image High Resolution Material Capturecited by 11
  21. 2021Variational Selective Autoencoder: Learning from Partially-Observed Heterogeneous Datacited by 10
  22. 2021Revisiting Bayesian Autoencoders with MCMCcited by 10
  23. 2020Regularized Inverse Reinforcement Learningcited by 9
  24. 2021Bayesian graph convolutional neural networks via tempered MCMCcited by 9
  25. 2023Precision-Recall Divergence Optimization for Generative Modeling with GANs and Normalizing Flowscited by 9
  26. 2023Supervised structure learningcited by 9
  27. 2021Deep Image Synthesis from Intuitive User Input: A Review and Perspectivescited by 8
  28. 2024Kernel Semi-Implicit Variational Inferencecited by 8
  29. 2021Reliable Estimation of KL Divergence using a Discriminator in Reproducing Kernel Hilbert Spacecited by 7
  30. 2022Gromov-Wasserstein Autoencoderscited by 7
  31. 2022Variational Laplace Autoencoderscited by 7
  32. 2021Inferential Wasserstein Generative Adversarial Networkscited by 6
  33. 2022Forget-me-not! Contrastive Critics for Mitigating Posterior Collapsecited by 6
  34. 2023Neural Operator Variational Inference based on Regularized Stein Discrepancy for Deep Gaussian Processescited by 6
  35. 2022Leveraging Relational Information for Learning Weakly Disentangled Representationscited by 5
  36. 2022Generative Bayesian Inference with GANscited by 5
  37. 2023Variational Classificationcited by 5
  38. 2023Implicit Variational Inference for High-Dimensional Posteriorscited by 5

50 most cited of 107 All 107 (JSON)