Metraipolis › archive › dc_c5c277ca342b

LP-NAS: Linear Programming-based Neural Architecture Search — arXiv:2608.14472

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.14472
License (as archived)
CC0-1.0
Archived
2026-10-19T02:21:34.860Z
SHA-256 of the archived text
506abeb0c3cb39c099cb6e73de549f0e75a9be1bf2c2f41d0eccb9096cb23406
Stable URL of this page
https://metraipolis.com/documento/dc_c5c277ca342b

How to cite

LP-NAS: Linear Programming-based Neural Architecture Search — arXiv:2608.14472 — arXiv (en), https://arxiv.org/abs/2608.14472 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c5c277ca342b (Metraipolis archive dc_c5c277ca342b, sha256 506abeb0c3cb39c099cb6e73de549f0e75a9be1bf2c2f41d0eccb9096cb23406)
BibTeX
@misc{dcc5c277ca342b,
  title = {LP-NAS: Linear Programming-based Neural Architecture Search — arXiv:2608.14472},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.14472},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c5c277ca342b; sha256 506abeb0c3cb39c099cb6e73de549f0e75a9be1bf2c2f41d0eccb9096cb23406},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.14472. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Neural Architecture Search (NAS) aims to automate neural network architecture design, reducing reliance on human expertise. Among the various NAS methods, differentiable NAS has gained prominence due to its efficiency and accuracy compared to conventional NAS approaches. Since differentiable NAS relaxes the architecture search space into a continuous domain, it is possible to apply principles from continuous optimization to NAS. In this paper, we propose Linear Programming-based NAS (LP-NAS), a mathematical programming-based framework for differentiable NAS that is applicable to a wide range of continuous search spaces. LP-NAS formulates a linear program (LP) using the validation-loss gradient and the training-loss Hessian to compute an architecture update direction that improves generalization while preserving the optimality of the model parameters. By following this LP-derived descent direction, LP-NAS efficiently navigates the architecture search space, leading to faster and more effective architecture optimization. We introduce two computationally efficient variants of LP-NAS, namely S-LP-NAS and R-LP-NAS. Applying LP-NAS to the Differentiable Architecture Search (DARTS) search space results in two algorithmic variants, S-LP-DARTS and R-LP-DARTS. Both variants achieve faster convergence and significantly higher validation performance during the early search iterations than the standard DARTS algorithm. Extensive experiments on CIFAR-10 and CIFAR-100 show that LP-DARTS outperforms standard DARTS in both the architecture search and evaluation phases. Additionally, we compare our approach with several DARTS variants (P-DARTS, PC-DARTS, and STO-DARTS) on the CIFAR-10 dataset and demonstrate its effectiveness. Furthermore, we validate the transferability of the discovered architectures through experiments on the ImageNet dataset.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-17 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.14472 — 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 2026-10-19T02:02:02.951Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).