Metraipolis › archive › dc_aebecf163b04
Sparsely connected neural network representation of Lagrange finite element function — arXiv:2609.23299
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.23299
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T21:42:32.812Z
- SHA-256 of the archived text
dc2c1500992b76eea6ba1c8103449385e3348a682ae10ea6faf50eb64fa2bebe- Stable URL of this page
https://metraipolis.com/documento/dc_aebecf163b04
How to cite
Sparsely connected neural network representation of Lagrange finite element function — arXiv:2609.23299 — arXiv (en), https://arxiv.org/abs/2609.23299 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_aebecf163b04 (Metraipolis archive dc_aebecf163b04, sha256 dc2c1500992b76eea6ba1c8103449385e3348a682ae10ea6faf50eb64fa2bebe)
BibTeX
@misc{dcaebecf163b04,
title = {Sparsely connected neural network representation of Lagrange finite element function — arXiv:2609.23299},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.23299},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_aebecf163b04; sha256 dc2c1500992b76eea6ba1c8103449385e3348a682ae10ea6faf50eb64fa2bebe},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.23299. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We construct a mesh-induced sparsely connected neural network framework that exactly reproduces arbitrary-order Lagrange finite element spaces over simplicial meshes. Unlike conventional black-box neural surrogates, the proposed network architecture is fully dictated by finite element discretization rules: local computations stem from simplex geometry and barycentric coordinate transformations, while global consistency is enforced through shared degrees of freedom. For linear Lagrange elements, local basis functions are directly implemented via affine barycentric layers, and high-order polynomial bases are explicitly decomposed into barycentric product compositions realized by specially designed $\mathrm{ReLU}^p$ modules. Equipped with element indicator branches and multiplication units, these modular local components are globally assembled into a sparsely connected neural network whose function space coincides exactly with the target finite element space, thereby inheriting the complete classical finite element approximation theory. By prescribing customized backward differentiation rules for piecewise activations, function values and their spatial gradients can be simultaneously extracted via automatic differentiation within a unified computational graph, eliminating the separate gradient calculation subroutines required in standard finite element implementations. Numerical experiments verify the accuracy of the neural network representation of Lagrange finite elements. Furthermore, by virtue of the intrinsic mesh-free nature of this neural network representation, finite element functions can be interpolated between non-matching meshes, and the proposed scheme can be applied to adaptive finite element methods for solving parabolic partial differential equations. An open-source code implementation of the proposed architecture is made publicly available.
Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-09-22 in math.NA).
Categorie arXiv: Numerical Analysis (math.NA).
Pagina del lavoro: https://arxiv.org/abs/2609.23299 — 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 2026-10-09T21:22:11.577Z dalla pagina https://arxiv.org/catchup/math.NA/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).