mlsanityData to 7 Oct 2026

Bayesian GAN

arXiv 1705.09558 ↗First posted 26 May 2017stat.ML cs.AI cs.CVcited by 31

Not on the map. Why?

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.

Key facts. Cited by 31 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 May 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 5; 2023: 9; 2024: 3; 2025: 6; 2026: 2.

31 papers.

Sort:

By area:

  1. 2023BayesDiff: Estimating Pixel-wise Uncertainty in Diffusion via Bayesian Inferencecited by 30
  2. 2022Particle algorithms for maximum likelihood training of latent variable modelscited by 26
  3. 2023Adversarial Bayesian Augmentation for Single-Source Domain Generalizationcited by 21
  4. 2025Generative Uncertainty in Diffusion Modelscited by 20
  5. 2024Diffusion Model Guided Sampling with Pixel-Wise Aleatoric Uncertainty Estimationcited by 17
  6. 2023Human-AI Interactions and Societal Pitfallscited by 9
  7. 2022Defending Black-box Skeleton-based Human Activity Classifierscited by 8
  8. 2024Capturing Climatic Variability: Using Deep Learning for Stochastic Downscalingcited by 7
  9. 2021MIND: Inductive Mutual Information Estimation, A Convex Maximum-Entropy Copula Approachcited by 6
  10. 2022Generative Bayesian Inference with GANscited by 5
  11. 2021Generative Adversarial Networks and Adversarial Autoencoders: Tutorial and Surveycited by 4
  12. 2021Sensor-invariant Fingerprint ROI Segmentation Using Recurrent Adversarial Learningcited by 2
19 more
  1. 2022Unsupervised Joint Image Transfer and Uncertainty Quantification Using Patch Invariant Networkscited by 2
  2. 2024Robust training of implicit generative models for multivariate and heavy-tailed distributions with an invariant statistical losscited by 2
  3. 2021Exploring Dropout Discriminator for Domain Adaptationcited by 1
  4. 2021Unsupervised Image Generation with Infinite Generative Adversarial Networkscited by 1
  5. 2022From MIM-Based GAN to Anomaly Detection:Event Probability Influence on Generative Adversarial Networkscited by 1
  6. 20233D GANs and Latent Space: A comprehensive surveycited by 1
  7. 2023Post-train Black-box Defense via Bayesian Boundary Correctioncited by 1
  8. 2025Semi-Supervised Bayesian GANs with Log-Signatures for Uncertainty-Aware Credit Card Fraud Detectioncited by 1
  9. 2021Prb-GAN: A Probabilistic Framework for GAN Modellingcited by 0
  10. 2023A New Paradigm for Generative Adversarial Networks based on Randomized Decision Rulescited by 0
  11. 2023Robust GAN inversioncited by 0
  12. 2023Mutual information maximizing quantum generative adversarial networkscited by 0
  13. 2023A Chronological Survey of Theoretical Advancements in Generative Adversarial Networks for Computer Visioncited by 0
  14. 2025Joint-stochastic-approximation Autoencoders with Application to Semi-supervised Learningcited by 0
  15. 2025Bridging GANs and Bayesian Neural Networks via Partial Stochasticitycited by 0
  16. 2025Extreme value forecasting using relevance-based data augmentation with deep learning modelscited by 0
  17. 2025BI-DCGAN: A Theoretically Grounded Bayesian Framework for Efficient and Diverse GANscited by 0
  18. 2026Bayesian Generative Adversarial Networks via Gaussian Approximation for Tabular Data Synthesiscited by 0
  19. 2026EMPURPLE: A Free Lunch for Diffusion Distillation based on the Information Bottleneckcited by 0