mlsanityData to 14 Oct 2026

Multiplicative Normalizing Flows for Variational Bayesian Neural Networks

arXiv 1703.01961 ↗First posted 6 Mar 2017stat.ML cs.LGcited by 157

Not on the map. Why?

Abstract (arXiv)

We reinterpret multiplicative noise in neural networks as auxiliary random variables that augment the approximate posterior in a variational setting for Bayesian neural networks. We show that through this interpretation it is both efficient and straightforward to improve the approximation by employing normalizing flows while still allowing for local reparametrizations and a tractable lower bound. In experiments we show that with this new approximation we can significantly improve upon classical mean field for Bayesian neural networks on both predictive accuracy as well as predictive uncertainty.

Key facts. Cited by 157 papers in the map (data through 14 Oct 2026). First posted on arXiv 6 Mar 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2020: 1; 2021: 48; 2022: 30; 2023: 27; 2024: 25; 2025: 22; 2026: 4.

157 papers.

Sort:

By area:

  1. 2021A Survey of Uncertainty in Deep Neural Networkscited by 680
  2. 2021What Are Bayesian Neural Network Posteriors Really Like?cited by 308
  3. 2021Bayesian Neural Network Priors Revisitedcited by 121
  4. 2021Epistemic Neural Networkscited by 120
  5. 2021Priors in Bayesian Deep Learning: A Reviewcited by 101
  6. 2023A Survey on Uncertainty Quantification Methods for Deep Learningcited by 81
  7. 2021Paragraph-level Rationale Extraction through Regularization: A case study on European Court of Human Rights Casescited by 77
  8. 2022ViewFool: Evaluating the Robustness of Visual Recognition to Adversarial Viewpointscited by 48
  9. 2021Posterior Meta-Replay for Continual Learningcited by 45
  10. 2021LiBRe: A Practical Bayesian Approach to Adversarial Detectioncited by 40
  11. 2021Infinitely Deep Bayesian Neural Networks with Stochastic Differential Equationscited by 38
  12. 2021Is MC Dropout Bayesian?cited by 35
38 more
  1. 2023A Rigorous Link between Deep Ensembles and (Variational) Bayesian Methodscited by 32
  2. 2022Universal approximation property of invertible neural networkscited by 30
  3. 2022Copula Conformal Prediction for Multi-step Time Series Forecastingcited by 29
  4. 2021A Bit More Bayesian: Domain-Invariant Learning with Uncertaintycited by 27
  5. 2023A Primer on Bayesian Neural Networks: Review and Debatescited by 27
  6. 2021Contextual Dropout: An Efficient Sample-Dependent Dropout Modulecited by 26
  7. 2022Conformal Prediction with Temporal Quantile Adjustmentscited by 25
  8. 2021Robustness via Cross-Domain Ensemblescited by 23
  9. 2021Uncertainty-Aware Reliable Text Classificationcited by 23
  10. 2021Generalized Normalizing Flows via Markov Chainscited by 23
  11. 2024HyperFast: Instant Classification for Tabular Datacited by 22
  12. 2023POCO: 3D Pose and Shape Estimation with Confidencecited by 21
  13. 2024Diffusive Gibbs Samplingcited by 21
  14. 2020Sequential Anomaly Detection using Inverse Reinforcement Learningcited by 20
  15. 2024Embedding Trajectory for Out-of-Distribution Detection in Mathematical Reasoningcited by 18
  16. 2021Bayesian OOD detection with aleatoric uncertainty and outlier exposurecited by 16
  17. 2021Sparse Uncertainty Representation in Deep Learning with Inducing Weightscited by 16
  18. 2021When in Doubt: Neural Non-Parametric Uncertainty Quantification for Epidemic Forecastingcited by 16
  19. 2023Uncertainty Quantification via Neural Posterior Principal Componentscited by 16
  20. 2021A Bayesian neural network predicts the dissolution of compact planetary systemscited by 15
  21. 2021Deep Learning for Bayesian Optimization of Scientific Problems with High-Dimensional Structurecited by 15
  22. 2022Posterior Refinement Improves Sample Efficiency in Bayesian Neural Networkscited by 14
  23. 2021Pathologies in priors and inference for Bayesian transformerscited by 13
  24. 2024Variational Bayesian Optimal Experimental Design with Normalizing Flowscited by 13
  25. 2021Uncertainty-Aware Deep Co-training for Semi-supervised Medical Image Segmentationcited by 12
  26. 2024Looks Too Good To Be True: An Information-Theoretic Analysis of Hallucinations in Generative Restoration Modelscited by 12
  27. 2022Conformal Methods for Quantifying Uncertainty in Spatiotemporal Data: A Surveycited by 11
  28. 2023Using AI Uncertainty Quantification to Improve Human Decision-Makingcited by 11
  29. 2024EigenVI: score-based variational inference with orthogonal function expansionscited by 11
  30. 2021Are Bayesian neural networks intrinsically good at out-of-distribution detection?cited by 10
  31. 2023Flat Seeking Bayesian Neural Networkscited by 10
  32. 2023Promises and Pitfalls of the Linearized Laplace in Bayesian Optimizationcited by 10
  33. 2024Epistemic Uncertainty Quantification For Pre-trained Neural Networkcited by 10
  34. 2022Conformal Prediction Intervals with Temporal Dependencecited by 9
  35. 2024Monotone, Bi-Lipschitz, and Polyak-Lojasiewicz Networkscited by 9
  36. 2022Learning Unbiased Transferability for Domain Adaptation by Uncertainty Modelingcited by 8
  37. 2022Tackling covariate shift with node-based Bayesian neural networkscited by 8
  38. 2022Confidence estimation of classification based on the distribution of the neural network output layercited by 8

50 most cited of 157 All 157 (JSON)