Metraipolis › archive › dc_61c6430eefcb

Local gradient neural operator — arXiv:2609.07752

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.07752
License (as archived)
CC0-1.0
Archived
2026-10-16T13:57:55.460Z
SHA-256 of the archived text
8cb17e8165f20c134c43d4e76097a898c5c11cfbb3720868e3d6a936595b2f18
Stable URL of this page
https://metraipolis.com/documento/dc_61c6430eefcb

How to cite

Local gradient neural operator — arXiv:2609.07752 — arXiv (en), https://arxiv.org/abs/2609.07752 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_61c6430eefcb (Metraipolis archive dc_61c6430eefcb, sha256 8cb17e8165f20c134c43d4e76097a898c5c11cfbb3720868e3d6a936595b2f18)
BibTeX
@misc{dc61c6430eefcb,
  title = {Local gradient neural operator — arXiv:2609.07752},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.07752},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_61c6430eefcb; sha256 8cb17e8165f20c134c43d4e76097a898c5c11cfbb3720868e3d6a936595b2f18},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.07752. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Field temporal prediction and source identification constitute canonical problems in dynamical systems. Conventional approaches to these problems depend on a thorough understanding of the governing partial differential equations (PDEs). Recently, deep learning, as represented by neural operators, has provided a data-driven paradigm for addressing such tasks. However, most existing global neural operators for PDEs require large training datasets and many learnable parameters, with limited interpretability and generalization. We propose the local gradient neural operator (LGNO) as a lightweight and interpretable alternative for field temporal evolution prediction and source identification in typical mechanical problems. The method builds on priors from nonlinear gradient discretization and uses multilayer perceptron convolutional layers to learn translation-invariant local kernels that resemble discrete stencils. A zero consistent stencil factorization separates coefficient learning from field reconstruction, rendering the learned operators more transparent. For problems with symmetries, network folding shares equivalent components and reduces parameter counts. We evaluate the method on PDE benchmarks covering linear and nonlinear, static and dynamic, and low and high dimensional cases. Results show that LGNO maintains accuracy, parameter efficiency, and rollout stability across these tasks, and further exhibits wide applicability to mechanical problems including diffusion, flow, and quantum phenomena.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Mathematical Physics (math-ph).
Pagina del lavoro: https://arxiv.org/abs/2609.07752 — 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 2026-10-16T13:39:42.986Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).