# Bayesian GAN

arXiv: https://arxiv.org/abs/1705.09558 · HTML: https://mlsanity.com/paper/1705.09558/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 May 2017.

## Built on by (most cited first, 30 of 32)

- [BayesDiff: Estimating Pixel-wise Uncertainty in Diffusion via Bayesian Inference](https://mlsanity.com/paper/2310.11142/) (2023)
- [Particle algorithms for maximum likelihood training of latent variable models](https://mlsanity.com/paper/2204.12965/) (2022)
- [Generative Uncertainty in Diffusion Models](https://mlsanity.com/paper/2502.20946/) (2025)
- [Adversarial Bayesian Augmentation for Single-Source Domain Generalization](https://mlsanity.com/paper/2307.09520/) (2023)
- [Diffusion Model Guided Sampling with Pixel-Wise Aleatoric Uncertainty Estimation](https://mlsanity.com/paper/2412.00205/) (2024)
- [Defending Black-box Skeleton-based Human Activity Classifiers](https://mlsanity.com/paper/2203.04713/) (2022)
- [Human-AI Interactions and Societal Pitfalls](https://mlsanity.com/paper/2309.10448/) (2023)
- [Capturing Climatic Variability: Using Deep Learning for Stochastic Downscaling](https://mlsanity.com/paper/2406.02587/) (2024)
- [MIND: Inductive Mutual Information Estimation, A Convex Maximum-Entropy Copula Approach](https://mlsanity.com/paper/2102.13182/) (2021)
- [Generative Bayesian Inference with GANs](https://mlsanity.com/paper/2208.12113/) (2022)
- [Generative Adversarial Networks and Adversarial Autoencoders: Tutorial and Survey](https://mlsanity.com/paper/2111.13282/) (2021)
- [Sensor-invariant Fingerprint ROI Segmentation Using Recurrent Adversarial Learning](https://mlsanity.com/paper/2107.01361/) (2021)
- [Unsupervised Joint Image Transfer and Uncertainty Quantification Using Patch Invariant Networks](https://mlsanity.com/paper/2207.04325/) (2022)
- [Robust training of implicit generative models for multivariate and heavy-tailed distributions with an invariant statistical loss](https://mlsanity.com/paper/2410.22381/) (2024)
- [Exploring Dropout Discriminator for Domain Adaptation](https://mlsanity.com/paper/2107.04231/) (2021)
- [Unsupervised Image Generation with Infinite Generative Adversarial Networks](https://mlsanity.com/paper/2108.07975/) (2021)
- [From MIM-Based GAN to Anomaly Detection:Event Probability Influence on Generative Adversarial Networks](https://mlsanity.com/paper/2203.13464/) (2022)
- [3D GANs and Latent Space: A comprehensive survey](https://mlsanity.com/paper/2304.03932/) (2023)
- [Post-train Black-box Defense via Bayesian Boundary Correction](https://mlsanity.com/paper/2306.16979/) (2023)
- [Semi-Supervised Bayesian GANs with Log-Signatures for Uncertainty-Aware Credit Card Fraud Detection](https://mlsanity.com/paper/2509.00931/) (2025)
- [Prb-GAN: A Probabilistic Framework for GAN Modelling](https://mlsanity.com/paper/2107.05241/) (2021)
- [A New Paradigm for Generative Adversarial Networks based on Randomized Decision Rules](https://mlsanity.com/paper/2306.13641/) (2023)
- [Robust GAN inversion](https://mlsanity.com/paper/2308.16510/) (2023)
- [Mutual information maximizing quantum generative adversarial networks](https://mlsanity.com/paper/2309.01363/) (2023)
- [A Chronological Survey of Theoretical Advancements in Generative Adversarial Networks for Computer Vision](https://mlsanity.com/paper/2311.00995/) (2023)
- [Joint-stochastic-approximation Autoencoders with Application to Semi-supervised Learning](https://mlsanity.com/paper/2505.18558/) (2025)
- [Bridging GANs and Bayesian Neural Networks via Partial Stochasticity](https://mlsanity.com/paper/2507.00651/) (2025)
- [Extreme value forecasting using relevance-based data augmentation with deep learning models](https://mlsanity.com/paper/2510.02407/) (2025)
- [BI-DCGAN: A Theoretically Grounded Bayesian Framework for Efficient and Diverse GANs](https://mlsanity.com/paper/2510.26892/) (2025)
- [Bayesian Generative Adversarial Networks via Gaussian Approximation for Tabular Data Synthesis](https://mlsanity.com/paper/2602.21948/) (2026)

## Abstract (arXiv)

Generative adversarial networks (GANs) can implicitly learn rich distributions over images, audio, and data which are hard to model with an explicit likelihood. We present a practical Bayesian formulation for unsupervised and semi-supervised learning with GANs. Within this framework, we use stochastic gradient Hamiltonian Monte Carlo to marginalize the weights of the generator and discriminator networks. The resulting approach is straightforward and obtains good performance without any standard interventions such as feature matching, or mini-batch discrimination. By exploring an expressive posterior over the parameters of the generator, the Bayesian GAN avoids mode-collapse, produces interpretable and diverse candidate samples, and provides state-of-the-art quantitative results for semi-supervised learning on benchmarks including SVHN, CelebA, and CIFAR-10, outperforming DCGAN, Wasserstein GANs, and DCGAN ensembles.