# Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks

arXiv: https://arxiv.org/abs/1701.04722 · HTML: https://mlsanity.com/paper/1701.04722/

## Key facts

- Cited by 107 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jan 2017.

## Built on by (most cited first, 30 of 107)

- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Self-Supervised Pretraining of 3D Features on any Point-Cloud](https://mlsanity.com/paper/2101.02691/) (2021)
- [Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flow](https://mlsanity.com/paper/1810.00821/) (2018)
- [Synthesizing Informative Training Samples with GAN](https://mlsanity.com/paper/2204.07513/) (2022)
- [Posterior Meta-Replay for Continual Learning](https://mlsanity.com/paper/2103.01133/) (2021)
- [KALE Flow: A Relaxed KL Gradient Flow for Probabilities with Disjoint Support](https://mlsanity.com/paper/2106.08929/) (2021)
- [GATSBI: Generative Adversarial Training for Simulation-Based Inference](https://mlsanity.com/paper/2203.06481/) (2022)
- [A survey of synthetic data augmentation methods in computer vision](https://mlsanity.com/paper/2403.10075/) (2024)
- [A Rigorous Link between Deep Ensembles and (Variational) Bayesian Methods](https://mlsanity.com/paper/2305.15027/) (2023)
- [Adversarial and Contrastive Variational Autoencoder for Sequential Recommendation](https://mlsanity.com/paper/2103.10693/) (2021)
- [Diagnosing and Fixing Manifold Overfitting in Deep Generative Models](https://mlsanity.com/paper/2204.07172/) (2022)
- [CaloMan: Fast generation of calorimeter showers with density estimation on learned manifolds](https://mlsanity.com/paper/2211.15380/) (2022)
- [Denoising diffusion algorithm for inverse design of microstructures with fine-tuned nonlinear material properties](https://mlsanity.com/paper/2302.12881/) (2023)
- [DP-Image: Differential Privacy for Image Data in Feature Space](https://mlsanity.com/paper/2103.07073/) (2021)
- [Spatiotemporal Self-supervised Learning for Point Clouds in the Wild](https://mlsanity.com/paper/2303.16235/) (2023)
- [Factor Analysis, Probabilistic Principal Component Analysis, Variational Inference, and Variational Autoencoder: Tutorial and Survey](https://mlsanity.com/paper/2101.00734/) (2021)
- [Biased Mixtures Of Experts: Enabling Computer Vision Inference Under Data Transfer Limitations](https://mlsanity.com/paper/2008.09662/) (2020)
- [Efficient Out-of-Distribution Detection Using Latent Space of β-VAE for Cyber-Physical Systems](https://mlsanity.com/paper/2108.11800/) (2021)
- [Stochastic Physics-Informed Neural Ordinary Differential Equations](https://mlsanity.com/paper/2109.01621/) (2021)
- [Semi-Implicit Variational Inference via Score Matching](https://mlsanity.com/paper/2308.10014/) (2023)
- [Variational inference with a quantum computer](https://mlsanity.com/paper/2103.06720/) (2021)
- [Lifelong Teacher-Student Network Learning](https://mlsanity.com/paper/2107.04689/) (2021)
- [Sliced Wasserstein Variational Inference](https://mlsanity.com/paper/2207.13177/) (2022)
- [Learning to Estimate 6DoF Pose from Limited Data: A Few-Shot, Generalizable Approach using RGB Images](https://mlsanity.com/paper/2306.07598/) (2023)
- [Sparse Inducing Points in Deep Gaussian Processes: Enhancing Modeling with Denoising Diffusion Variational Inference](https://mlsanity.com/paper/2407.17033/) (2024)
- [Generative Models in Decision Making: A Survey](https://mlsanity.com/paper/2502.17100/) (2025)
- [Mind the Gap when Conditioning Amortised Inference in Sequential Latent-Variable Models](https://mlsanity.com/paper/2101.07046/) (2021)
- [Hierarchical Semi-Implicit Variational Inference with Application to Diffusion Model Acceleration](https://mlsanity.com/paper/2310.17153/) (2023)
- [Function-space Inference with Sparse Implicit Processes](https://mlsanity.com/paper/2110.07618/) (2021)
- [Uncertainty-Aware Pedestrian Trajectory Prediction via Distributional Diffusion](https://mlsanity.com/paper/2303.08367/) (2023)

## 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.