mlsanityData to 7 Oct 2026

Radial Bayesian Neural Networks: Beyond Discrete Support In Large-Scale Bayesian Deep Learning

arXiv 1907.00865 ↗First posted 1 Jul 2019stat.ML cs.LGcited by 37

Not on the map. Why?

Abstract (arXiv)

We propose Radial Bayesian Neural Networks (BNNs): a variational approximate posterior for BNNs which scales well to large models while maintaining a distribution over weight-space with full support. Other scalable Bayesian deep learning methods, like MC dropout or deep ensembles, have discrete support-they assign zero probability to almost all of the weight-space. Unlike these discrete support methods, Radial BNNs' full support makes them suitable for use as a prior for sequential inference. In addition, they solve the conceptual challenges with the a priori implausibility of weight distributions with discrete support. The Radial BNN is motivated by avoiding a sampling problem in 'mean-field' variational inference (MFVI) caused by the so-called 'soap-bubble' pathology of multivariate Gaussians. We show that, unlike MFVI, Radial BNNs are robust to hyperparameters and can be efficiently applied to a challenging real-world medical application without needing ad-hoc tweaks and intensive tuning. In fact, in this setting Radial BNNs out-perform discrete-support methods like MC dropout. Lastly, by using Radial BNNs as a theoretically principled, robust alternative to MFVI we make significant strides in a Bayesian continual learning evaluation.

Key facts. Cited by 37 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 Jul 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 9; 2023: 7; 2024: 5; 2025: 3; 2026: 3.

37 papers.

Sort:

By area:

  1. 2022Plex: Towards Reliability using Pretrained Large Model Extensionscited by 102
  2. 2021Priors in Bayesian Deep Learning: A Reviewcited by 101
  3. 2021Active Testing: Sample-Efficient Model Evaluationcited by 82
  4. 2021Uncertainty Baselines: Benchmarks for Uncertainty & Robustness in Deep Learningcited by 81
  5. 2024Variational Bayesian Last Layerscited by 67
  6. 2022Benchmarking Bayesian Deep Learning on Diabetic Retinopathy Detection Taskscited by 49
  7. 2021Posterior Meta-Replay for Continual Learningcited by 45
  8. 2023Tractable Function-Space Variational Inference in Bayesian Neural Networkscited by 41
  9. 2022Active Surrogate Estimators: An Active Learning Approach to Label-Efficient Model Evaluationcited by 26
  10. 2021Feature Generation and Hypothesis Verification for Reliable Face Anti-Spoofingcited by 23
  11. 2022On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrationscited by 18
  12. 2021Heavy-tailed denoising score matchingcited by 17
25 more
  1. 2024Predictive Churn with the Set of Good Modelscited by 15
  2. 2023Riemannian Laplace approximations for Bayesian neural networkscited by 14
  3. 2026InfoNCE Induces Gaussian Distributioncited by 14
  4. 2023Drug Discovery under Covariate Shift with Domain-Informed Prior Distributions over Functionscited by 10
  5. 2023A Benchmark on Uncertainty Quantification for Deep Learning Prognosticscited by 9
  6. 2022Uncertainty-aware deep learning methods for robust diabetic retinopathy classificationcited by 8
  7. 2021Bayesian Neural Networks: Essentialscited by 7
  8. 2023On Sequential Bayesian Inference for Continual Learningcited by 6
  9. 2022Dual Accuracy-Quality-Driven Neural Network for Prediction Interval Generationcited by 5
  10. 2021Bayesian Deep Neural Networks for Supervised Learning of Single-View Depthcited by 3
  11. 2022Graph Reparameterizations for Enabling 1000+ Monte Carlo Iterations in Bayesian Deep Neural Networkscited by 3
  12. 2022Deep Combinatorial Aggregationcited by 3
  13. 2024Model and Feature Diversity for Bayesian Neural Networks in Mutual Learningcited by 2
  14. 2021Efficient Action Recognition Using Confidence Distillationcited by 1
  15. 2021Spatial-Temporal-Fusion BNN: Variational Bayesian Feature Layercited by 1
  16. 2023Uncertainty estimation in Deep Learning for Panoptic segmentationcited by 1
  17. 2024Inadequacy of common stochastic neural networks for reliable clinical decision supportcited by 1
  18. 2025DEF: Diffusion-augmented Ensemble Forecastingcited by 1
  19. 2026Trajectory Stitching for Solving Inverse Problems with Flow-Based Modelscited by 1
  20. 2022Radial Spike and Slab Bayesian Neural Networks for Sparse Data in Ransomware Attackscited by 0
  21. 2023Function-Space Regularization for Deep Bayesian Classificationcited by 0
  22. 2024On Uniform, Bayesian, and PAC-Bayesian Deep Ensemblescited by 0
  23. 2025Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Priorcited by 0
  24. 2025Precise Bayesian Neural Networkscited by 0
  25. 2026Confidence-Uncertainty Boundary Calibration for Bayesian Deep Learning in Medical Image Analysiscited by 0