Metraipolis › archive › dc_710f37a61649
SINO: Scale-Invariant Neural Operator — arXiv:2609.36890
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.36890
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T17:30:00.667Z
- SHA-256 of the archived text
263eaba2367b8832cbb606e2349d4a1376c0d87af523474b15f2536ae1d19e8f- Stable URL of this page
https://metraipolis.com/documento/dc_710f37a61649
How to cite
SINO: Scale-Invariant Neural Operator — arXiv:2609.36890 — arXiv (en), https://arxiv.org/abs/2609.36890 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_710f37a61649 (Metraipolis archive dc_710f37a61649, sha256 263eaba2367b8832cbb606e2349d4a1376c0d87af523474b15f2536ae1d19e8f)
BibTeX
@misc{dc710f37a61649,
title = {SINO: Scale-Invariant Neural Operator — arXiv:2609.36890},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.36890},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_710f37a61649; sha256 263eaba2367b8832cbb606e2349d4a1376c0d87af523474b15f2536ae1d19e8f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36890. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
In scientific machine learning, physical fields governed by partial differential equations exhibit low-rank structure and scale invariance. When solving equations on coarse grids, missing information leads to the closure problem: modeling unresolved physics to recover lost dynamics. Although closure terms depend on grid resolution, they represent scale-invariant physical laws. A model truly learning physics should capture these mechanisms with low-rank parameterization rather than memorizing grid-specific patterns. Inspired by this, we propose the Scale-Invariant Neural Operator (SINO), which learns on normalized physical scales via a dual-branch architecture operating in spectral and spatial domains. SINO uses bottleneck MLPs to generate continuous convolution kernels, embedding an explicit low-rank inductive bias that concentrates more than 95 percent of variance in 2-3 modes, as validated by PCA across benchmarks, while drastically reducing parameters. This principled design yields 38 times steeper scaling law exponents than FNO, demonstrating superior parameter efficiency. We compare SINO with traditional models (U-Net, DeepONet), Transformer models (Transolver, Oformer, GK-Transformer), and frequency-domain models (FNO, AMFNO, UFNO) on closure problems spanning externally forced Burgers turbulence, decaying Burgers turbulence, KS turbulence, Kolmogorov-forced NS turbulence, and decaying NS turbulence. Experiments show SINO achieves 1.5-38 times error reduction and 2-23 times parameter efficiency over baselines, with superior scaling laws reflecting exceptional data efficiency from principled low-rank design. Code is available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.36890 — 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 2026-10-07T16:59:48.264Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).