# Maxwell's Demon at Work: Efficient Pruning by Leveraging Saturation of Neurons

Source: [Maxwell's Demon at Work: Efficient Pruning by Leveraging Saturation of Neurons](<https://www.sota2.com/research/paper/68fa79f41e209131cea803bc>)

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

Data updated: 2026-01-02T05:00:04.167Z

Authors: Simon Dufort-Labb\\'e, Pierluca D'Oro, Evgenii Nikishin, Razvan Pascanu, Pierre-Luc Bacon, Aristide Baratin

Published: 2024-03-12T14:28:06.000Z

## Abstract

When training neural networks, dying neurons -- units becoming inactive or saturated -- are traditionally seen as harmful. This paper sheds new light on this phenomenon. By exploring the impact of various hyperparameter configurations on dying neurons during training, we gather insights on how to improve upon sparse training approaches to pruning. We introduce Demon Pruning (DemP), a method that controls the proliferation of dead neurons through a combination of noise injection on active units and a one-cycle schedule regularization strategy, dynamically leading to network sparsity. Experiments on CIFAR-10 and ImageNet datasets demonstrate that DemP outperforms existing dense-to-sparse structured pruning methods, achieving better accuracy-sparsity tradeoffs and accelerating training by up to 3.56$\\times$. These findings provide a novel perspective on dying neurons as a resource for efficient model compression and optimization.

## 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/2403.07688>)

[PDF](<https://arxiv.org/pdf/2403.07688.pdf>)