# On the Effects of Quantisation on Model Uncertainty in Bayesian Neural Networks

arXiv: https://arxiv.org/abs/2102.11062 · HTML: https://mlsanity.com/paper/2102.11062/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 30 references that are in the map.
- First posted on arXiv 22 Feb 2021.

## Builds on (most cited first, 16 of 16)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [Weight Uncertainty in Neural Networks](https://mlsanity.com/paper/1505.05424/) (2015)
- [Quantizing deep convolutional networks for efficient inference: A whitepaper](https://mlsanity.com/paper/1806.08342/) (2018)
- [Stochastic Gradient Hamiltonian Monte Carlo](https://mlsanity.com/paper/1402.4102/) (2014)
- [Black Box Variational Inference](https://mlsanity.com/paper/1401.0118/) (2013)
- [Low-bit Quantization of Neural Networks for Efficient Inference](https://mlsanity.com/paper/1902.06822/) (2019)
- [Bayesian Bits: Unifying Quantization and Pruning](https://mlsanity.com/paper/2005.07093/) (2020)
- [VIBNN: Hardware Acceleration of Bayesian Neural Networks](https://mlsanity.com/paper/1802.00822/) (2018)
- [A Survey of FPGA-Based Neural Network Accelerator](https://mlsanity.com/paper/1712.08934/) (2017)
- [Variational Gaussian Dropout is not Bayesian](https://mlsanity.com/paper/1711.02989/) (2017)
- [Sampling-Free Learning of Bayesian Quantized Neural Networks](https://mlsanity.com/paper/1912.02992/) (2019)

## Built on by (most cited first, 8 of 8)

- [Bayesian Learning via Neural Schr"odinger-F"ollmer Flows](https://mlsanity.com/paper/2111.10510/) (2021)
- [Low-Precision Stochastic Gradient Langevin Dynamics](https://mlsanity.com/paper/2206.09909/) (2022)
- [Stochastic Weight Sharing for Bayesian Neural Networks](https://mlsanity.com/paper/2505.17856/) (2025)
- [Ex Uno Pluria: Insights on Ensembling in Low Precision Number Systems](https://mlsanity.com/paper/2411.14860/) (2024)
- [Uncertainty Quantification in Detecting Choroidal Metastases on MRI via Evolutionary Strategies](https://mlsanity.com/paper/2404.08853/) (2024)
- [Enhancing Dropout-based Bayesian Neural Networks with Multi-Exit on FPGA](https://mlsanity.com/paper/2406.14593/) (2024)
- [Uncertainty-Preserving QBNNs: Multi-Level Quantization of SVI-Based Bayesian Neural Networks for Image Classification](https://mlsanity.com/paper/2512.10602/) (2025)
- [Constrained Co-Design for Photonic Bayesian Neural Networks](https://mlsanity.com/paper/2608.02229/) (2026)

## Abstract (arXiv)

Bayesian neural networks (BNNs) are making significant progress in many research areas where decision-making needs to be accompanied by uncertainty estimation. Being able to quantify uncertainty while making decisions is essential for understanding when the model is over-/under-confident, and hence BNNs are attracting interest in safety-critical applications, such as autonomous driving, healthcare, and robotics. Nevertheless, BNNs have not been as widely used in industrial practice, mainly because of their increased memory and compute costs. In this work, we investigate quantisation of BNNs by compressing 32-bit floating-point weights and activations to their integer counterparts, that has already been successful in reducing the compute demand in standard pointwise neural networks. We study three types of quantised BNNs, we evaluate them under a wide range of different settings, and we empirically demonstrate that a uniform quantisation scheme applied to BNNs does not substantially decrease their quality of uncertainty estimation.