# Multiplicative Normalizing Flows for Variational Bayesian Neural Networks

arXiv: https://arxiv.org/abs/1703.01961 · HTML: https://mlsanity.com/paper/1703.01961/

## Key facts

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

## Built on by (most cited first, 30 of 157)

- [A Survey of Uncertainty in Deep Neural Networks](https://mlsanity.com/paper/2107.03342/) (2021)
- [What Are Bayesian Neural Network Posteriors Really Like?](https://mlsanity.com/paper/2104.14421/) (2021)
- [Bayesian Neural Network Priors Revisited](https://mlsanity.com/paper/2102.06571/) (2021)
- [Epistemic Neural Networks](https://mlsanity.com/paper/2107.08924/) (2021)
- [Priors in Bayesian Deep Learning: A Review](https://mlsanity.com/paper/2105.06868/) (2021)
- [A Survey on Uncertainty Quantification Methods for Deep Learning](https://mlsanity.com/paper/2302.13425/) (2023)
- [Paragraph-level Rationale Extraction through Regularization: A case study on European Court of Human Rights Cases](https://mlsanity.com/paper/2103.13084/) (2021)
- [ViewFool: Evaluating the Robustness of Visual Recognition to Adversarial Viewpoints](https://mlsanity.com/paper/2210.03895/) (2022)
- [Posterior Meta-Replay for Continual Learning](https://mlsanity.com/paper/2103.01133/) (2021)
- [LiBRe: A Practical Bayesian Approach to Adversarial Detection](https://mlsanity.com/paper/2103.14835/) (2021)
- [Infinitely Deep Bayesian Neural Networks with Stochastic Differential Equations](https://mlsanity.com/paper/2102.06559/) (2021)
- [Is MC Dropout Bayesian?](https://mlsanity.com/paper/2110.04286/) (2021)
- [A Rigorous Link between Deep Ensembles and (Variational) Bayesian Methods](https://mlsanity.com/paper/2305.15027/) (2023)
- [Universal approximation property of invertible neural networks](https://mlsanity.com/paper/2204.07415/) (2022)
- [Copula Conformal Prediction for Multi-step Time Series Forecasting](https://mlsanity.com/paper/2212.03281/) (2022)
- [A Bit More Bayesian: Domain-Invariant Learning with Uncertainty](https://mlsanity.com/paper/2105.04030/) (2021)
- [A Primer on Bayesian Neural Networks: Review and Debates](https://mlsanity.com/paper/2309.16314/) (2023)
- [Contextual Dropout: An Efficient Sample-Dependent Dropout Module](https://mlsanity.com/paper/2103.04181/) (2021)
- [Conformal Prediction with Temporal Quantile Adjustments](https://mlsanity.com/paper/2205.09940/) (2022)
- [Robustness via Cross-Domain Ensembles](https://mlsanity.com/paper/2103.10919/) (2021)
- [Uncertainty-Aware Reliable Text Classification](https://mlsanity.com/paper/2107.07114/) (2021)
- [Generalized Normalizing Flows via Markov Chains](https://mlsanity.com/paper/2111.12506/) (2021)
- [HyperFast: Instant Classification for Tabular Data](https://mlsanity.com/paper/2402.14335/) (2024)
- [POCO: 3D Pose and Shape Estimation with Confidence](https://mlsanity.com/paper/2308.12965/) (2023)
- [Diffusive Gibbs Sampling](https://mlsanity.com/paper/2402.03008/) (2024)
- [Sequential Anomaly Detection using Inverse Reinforcement Learning](https://mlsanity.com/paper/2004.10398/) (2020)
- [Embedding Trajectory for Out-of-Distribution Detection in Mathematical Reasoning](https://mlsanity.com/paper/2405.14039/) (2024)
- [Bayesian OOD detection with aleatoric uncertainty and outlier exposure](https://mlsanity.com/paper/2102.12959/) (2021)
- [Sparse Uncertainty Representation in Deep Learning with Inducing Weights](https://mlsanity.com/paper/2105.14594/) (2021)
- [When in Doubt: Neural Non-Parametric Uncertainty Quantification for Epidemic Forecasting](https://mlsanity.com/paper/2106.03904/) (2021)

## 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.