Metraipolis › archive › dc_44fe58e42f02

Numerical Neural Operator: Connection Between Numerical Analysis and the Operator Learning and Building Discretized Neural Operators from Finite Element Methods — arXiv:2610.11120

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.11120
License (as archived)
CC0-1.0
Archived
2026-10-09T06:28:38.255Z
SHA-256 of the archived text
874882fbc19e57c22204647c175713b1636aac2c1ff61ddd9cf1e24101385621
Stable URL of this page
https://metraipolis.com/documento/dc_44fe58e42f02

How to cite

Numerical Neural Operator: Connection Between Numerical Analysis and the Operator Learning and Building Discretized Neural Operators from Finite Element Methods — arXiv:2610.11120 — arXiv (en), https://arxiv.org/abs/2610.11120 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_44fe58e42f02 (Metraipolis archive dc_44fe58e42f02, sha256 874882fbc19e57c22204647c175713b1636aac2c1ff61ddd9cf1e24101385621)
BibTeX
@misc{dc44fe58e42f02,
  title = {Numerical Neural Operator: Connection Between Numerical Analysis and the Operator Learning and Building Discretized Neural Operators from Finite Element Methods — arXiv:2610.11120},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.11120},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_44fe58e42f02; sha256 874882fbc19e57c22204647c175713b1636aac2c1ff61ddd9cf1e24101385621},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.11120. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Operator learning aims to learn mappings between function spaces and has been widely used for PDE-related problems. This raises two fundamental questions. First, is there a connection between standard numerical methods and neural operators, given that both are designed to approximate PDE solution operators? Second, when a neural operator is trained on numerically generated data, does it approximate the underlying infinite dimension operator, the training data themselves, or the discretized numerical scheme used to generate them? A key hypothesis in the paper is that the trained neural operator may mimic the discretized numerical schemes that generate the training data. The hypothesis has been partially and preliminary verified by the linear approximation principle proposed in Chen Chen 1995 paper and the following scaling law papers. However, neural operator approximation from the perspective of numerical discretization remains unexplored. In this work, we consider a class of PDEs and derive neural operator architectures from the numerical schemes. Firstly, the numerical basis functions, such as finite element basis functions, can be approximated or directly constructed by learnable neural networks. Then the finite difference schemes for temporal discretization can be unrolled into iterative neural architectures that generate the coefficients of the basis of the resulting neural operator. By leveraging numerical analysis, we establish convergence error estimates for these numerically derived neural operators. Notably, the network size depends polynomial on the approximation error in $L_2$, improving the nested exponential dependence derived in the general neural operator approximation and aligning with the numerical observations. Finally, numerical experiments demonstrate reduced errors and improved parameter efficiency.

Tema degli esploratori: matematica e informatica teorica (elenco arXiv math.NA, nuovi lavori del giorno).
Categorie arXiv: Numerical Analysis (math.NA).
Pagina del lavoro: https://arxiv.org/abs/2610.11120 — 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 2026-10-09T05:53:16.498Z dalla pagina https://arxiv.org/list/math.NA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).