Metraipolis › archive › dc_bde2a59797e8

Task-Aware Discretization of Differentiable Logic Gate Networks — arXiv:2609.33747

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.33747
License (as archived)
CC0-1.0
Archived
2026-10-07T22:37:45.167Z
SHA-256 of the archived text
3ce578a1ce44734a03c3009777157db1e4f5bcd6160b32de4e01846845296656
Stable URL of this page
https://metraipolis.com/documento/dc_bde2a59797e8

How to cite

Task-Aware Discretization of Differentiable Logic Gate Networks — arXiv:2609.33747 — arXiv (en), https://arxiv.org/abs/2609.33747 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bde2a59797e8 (Metraipolis archive dc_bde2a59797e8, sha256 3ce578a1ce44734a03c3009777157db1e4f5bcd6160b32de4e01846845296656)
BibTeX
@misc{dcbde2a59797e8,
  title = {Task-Aware Discretization of Differentiable Logic Gate Networks — arXiv:2609.33747},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.33747},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bde2a59797e8; sha256 3ce578a1ce44734a03c3009777157db1e4f5bcd6160b32de4e01846845296656},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33747. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Differentiable logic gate networks (DLGNs) enable gradient-based training of highly efficient Boolean networks by relaxing discrete logic gates during training and discretizing them for inference. Standard approaches make this discretization decision locally, typically through argmax selection and confidence- or entropy-based convergence criteria. We show that local discretization can be task-suboptimal even for globally optimal relaxed solutions, with high gate confidence providing no general guarantee, and derive bounds relating task-aware gate selection to tractable interventions in the relaxed network. Motivated by these results, we study first-order downstream task information for progressive discretization and characterize when this local approximation is reliable. Experiments on convolutional DLGNs reveal a strong locality dependence: first-order scores become unreliable when directly optimized over nonlocal interventions, but accurately assess local argmax decisions for progressive freezing.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Logic in Computer Science (cs.LO).
Pagina del lavoro: https://arxiv.org/abs/2609.33747 — 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 2026-10-07T22:14:28.034Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).