# BitPruning: Learning Bitlengths for Aggressive and Accurate Quantization

Source: [BitPruning: Learning Bitlengths for Aggressive and Accurate Quantization](<https://www.sota2.com/research/paper/68fa682c1e209131cea1a889>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:56:44.092Z

Authors: Milo\\v{s} Nikoli\\'c, Ghouthi Boukli Hacene, Ciaran Bannon, Alberto Delmas Lascorz, Matthieu Courbariaux, Yoshua Bengio, Vincent Gripon, Andreas Moshovos

Published: 2020-02-08T04:58:33.000Z

## Abstract

Neural networks have demonstrably achieved state-of-the art accuracy using low-bitlength integer quantization, yielding both execution time and energy benefits on existing hardware designs that support short bitlengths. However, the question of finding the minimum bitlength for a desired accuracy remains open. We introduce a training method for minimizing inference bitlength at any granularity while maintaining accuracy. Namely, we propose a regularizer that penalizes large bitlength representations throughout the architecture and show how it can be modified to minimize other quantifiable criteria, such as number of operations or memory footprint. We demonstrate that our method learns thrifty representations while maintaining accuracy. With ImageNet, the method produces an average per layer bitlength of 4.13, 3.76 and 4.36 bits on AlexNet, ResNet18 and MobileNet V2 respectively, remaining within 2.0%, 0.5% and 0.5% of the base TOP-1 accuracy.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2002.03090>)

[PDF](<https://arxiv.org/pdf/2002.03090.pdf>)