---
markdown_generated_at: "2026-10-14"
title: "Bayesian Bits: Unifying Quantization and Pruning"
url: "https://www.qualcomm.com/research/artificial-intelligence/papers-with-code/paper-7"
description: "Bayesian Bits 2020: AI research for adaptive precision. Read about the details, innovative methods, and its impact on machine learning."
canonicalUrl: "https://www.qualcomm.com/research/artificial-intelligence/papers-with-code/paper-7"
---

# Bayesian Bits: Unifying Quantization and Pruning

PAPER 7

Mart van Baalen
Christos Louizos
Markus Nagel
Rana Ali Amjad
Ying Wang
Tijmen Blankevoort
Max Welling (Qualcomm AI Research)

CVPR 2020

![](https://s7d1.scene7.com/is/image/dmqualcommprod/Papers-with-Code-Bayesian-Bits-800x439?$QC_Responsive$&fmt=png-alpha)

## Summary

The Bayesian bits method works a bit like a sequence of gates. Given a dataset, it first determines if there is enough evidence to include a parameter in the computation. If it has decided it is a useful parameter it continues to determine if a second bit is needed to represent it. This process continues until a gate closes, implying that all less significant bits will be removed. Through this idea the method can adaptively determine the necessary precision for a computation and save energy in the process.

[![](https://s7d1.scene7.com/is/image/dmqualcommprod/document-icon-v2_2?$QC_Responsive$&fmt=png-alpha)

#### Paper](https://arxiv.org/abs/2005.07093)

[![](https://s7d1.scene7.com/is/image/dmqualcommprod/code-icon_2?$QC_Responsive$&fmt=png-alpha)

#### Code](https://github.com/Qualcomm-AI-research/BayesianBits)

## Citation

*@inproceedings{baalen2020bayesianbits, title={Bayesian Bits: Unifying Quantization and Pruning}, author={Baalen, Mart van and Louizos, Christos and Nagel, Markus and Amjad, Rana Ali and Wang, Ying and Blankevoort, Tijmen and Welling, Max}, booktitle={Advances in Neural Information Processing Systems 33}, year={2020} }*

## Results

The experiments validate the proposed method on several benchmark datasets and show that it can learn pruned, mixed precision networks that provide a better trade-off between accuracy and efficiency than their static bit width equivalents.

## Looking for more papers with code?

[View all papers](https://www.qualcomm.com/research/artificial-intelligence/papers-with-code)

\* Qualcomm AI Research is an initiative of Qualcomm Technologies, Inc.