Metraipolis › archive › dc_e0347ee3fa36

Overcoming Kernel Redundancy for Scaling Logic Gate Networks — arXiv:2610.01069

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.01069
License (as archived)
CC0-1.0
Archived
2026-10-06T19:12:25.537Z
SHA-256 of the archived text
39675b05a7a8e99f7500dd73db348329691b0f8191ce3eb9986812c8584d4c9e
Stable URL of this page
https://metraipolis.com/documento/dc_e0347ee3fa36

How to cite

Overcoming Kernel Redundancy for Scaling Logic Gate Networks — arXiv:2610.01069 — arXiv (en), https://arxiv.org/abs/2610.01069 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e0347ee3fa36 (Metraipolis archive dc_e0347ee3fa36, sha256 39675b05a7a8e99f7500dd73db348329691b0f8191ce3eb9986812c8584d4c9e)
BibTeX
@misc{dce0347ee3fa36,
  title = {Overcoming Kernel Redundancy for Scaling Logic Gate Networks — arXiv:2610.01069},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.01069},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e0347ee3fa36; sha256 39675b05a7a8e99f7500dd73db348329691b0f8191ce3eb9986812c8584d4c9e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.01069. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Differentiable logic gate networks, which operate using only logic gates, have recently attracted attention as an efficient alternative to conventional neural networks. However, despite their efficiency, the scaling behavior of logic gate networks remains underexplored. By contrast, scaling model capacity is a central design principle in deep neural networks and typically leads to improved performance. This discrepancy raises a key question: Can similar scaling benefits also be achieved in logic gate networks? In this work, we focus on width as a primary scaling axis and conduct a systematic analysis of its behavior in logic gate networks. We observe that naive width scaling often introduces redundancy among logic kernels, limiting the effective use of additional kernels and leading to performance saturation. To address this limitation, we propose a dynamic logic kernel framework that reorganizes kernel utilization by promoting specialization across kernel groups. This enables the network to better utilize increased width via input-dependent kernel routing, while ensuring that both routing and computation are implemented entirely with gate-level Boolean operations at inference time. We further find that kernel redundancy is most pronounced at the first gate level, motivating an early-stage dynamic logic kernel strategy that concentrates adaptation at this level. Experimental results demonstrate that our approach improves kernel utilization and increases kernel diversity, leading to higher accuracy with improved parameter efficiency.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-02 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.01069 — 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 2026-10-06T17:37:36.733Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).