Metraipolis › archive › dc_d96f2f76ca07
Pruning Binarized Neural Networks: A Dedicated Framework and Globally Weighted Algorithms — arXiv:2608.26233
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.26233
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T16:09:12.684Z
- SHA-256 of the archived text
2bad01acf173cdead3e0e684237906a5b25c913480d7b7ac5183913f0550f81f- Stable URL of this page
https://metraipolis.com/documento/dc_d96f2f76ca07
How to cite
Pruning Binarized Neural Networks: A Dedicated Framework and Globally Weighted Algorithms — arXiv:2608.26233 — arXiv (en), https://arxiv.org/abs/2608.26233 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d96f2f76ca07 (Metraipolis archive dc_d96f2f76ca07, sha256 2bad01acf173cdead3e0e684237906a5b25c913480d7b7ac5183913f0550f81f)
BibTeX
@misc{dcd96f2f76ca07,
title = {Pruning Binarized Neural Networks: A Dedicated Framework and Globally Weighted Algorithms — arXiv:2608.26233},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.26233},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d96f2f76ca07; sha256 2bad01acf173cdead3e0e684237906a5b25c913480d7b7ac5183913f0550f81f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.26233. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Extreme compression of deep neural networks, up to full binarization, dramatically reduces memory footprint and arithmetic complexity, facilitating deployment on constrained edge hardware with field-programmable gate arrays (FPGAs) and microcontrollers. Although combining binarization with pruning promises additional efficiency gains, existing pruning strategies are ill-suited to binarized representations and rarely translate into meaningful hardware savings. We introduce a PyTorch-based, research-oriented framework that incorporates freezing and pruning mechanisms for designing and optimizing binarized neural networks. The framework enables rapid and reproducible evaluation of state-of-the-art approaches and the fast prototyping of new ones. Leveraging this framework, we propose a novel pruning method that accounts for the relative importance of learned parameters across abstraction levels. Such a global weighting mechanism consistently achieves a superior trade-off between model accuracy and pruning rate, achieving a 70% pruning rate on VGG11 with constant accuracy, while state-of-the-art results reach only 41% in the binarized setting. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-28 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.26233 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T15:34:49.886Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).