Metraipolis › archive › dc_72e48bd8df08

IGA-KAN: Isogeometric Analysis with Physics-Informed Closed-Form Kolmogorov-Arnold Networks for Forward and Inverse PDEs — arXiv:2610.06348

Source
arXiv
Original
https://arxiv.org/abs/2610.06348
License (as archived)
CC0-1.0
Archived
2026-10-06T05:32:30.168Z
SHA-256 of the archived text
1c5ae7b8f7bf1b2a58512cab2aa9cb6a0267199e6a3e5a5da62dde9e5f050970
Stable URL of this page
https://metraipolis.com/documento/dc_72e48bd8df08

How to cite

IGA-KAN: Isogeometric Analysis with Physics-Informed Closed-Form Kolmogorov-Arnold Networks for Forward and Inverse PDEs — arXiv:2610.06348 — arXiv, https://arxiv.org/abs/2610.06348 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_72e48bd8df08 (Metraipolis archive dc_72e48bd8df08, sha256 1c5ae7b8f7bf1b2a58512cab2aa9cb6a0267199e6a3e5a5da62dde9e5f050970)
BibTeX
@misc{dc72e48bd8df08,
  title = {IGA-KAN: Isogeometric Analysis with Physics-Informed Closed-Form Kolmogorov-Arnold Networks for Forward and Inverse PDEs — arXiv:2610.06348},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.06348},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_72e48bd8df08; sha256 1c5ae7b8f7bf1b2a58512cab2aa9cb6a0267199e6a3e5a5da62dde9e5f050970},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.06348. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Isogeometric analysis (IGA) solves partial differential equations accurately on exact NURBS geometry, whereas neural solvers are mesh-free but often orders of magnitude less accurate and typically trained by non-convex optimization without error control. We propose IGA-KAN, which uses local Kolmogorov-Arnold networks, fitted in closed form, to improve the IGA solution instead of replacing it. An IGA Galerkin solve produces u_h; on every knot-vertex patch a Kolmogorov-Arnold ridge model is fitted to the strong form of the equation, the exact boundary data and u_h, and the models are blended by IGA hat functions. With fixed inner functions the fit is one batched linear least-squares problem, without optimizer, learning rate or initialization. An a posteriori safeguard, motivated by a maximum-principle bound, decides where local models are used, keeping the IGA solution elsewhere. On eight benchmarks with exact solutions, five from the literature and one also posed on a domain fitted to a brain slice from MRI, the method reduces the error of IGA, at an unchanged number of Galerkin unknowns, by factors of 4.2 to 90 in L^2 and 4.1 to 220 in H^1 on the reference meshes, and its L^2 error is 6 to 6x10^4 times smaller than that of the best Kolmogorov-Arnold network trained from scratch on the same equations with a fixed budget. In an inverse problem it recovers an unknown constant source from one noise-free observation 167 times more accurately than IGA. The gain is attributed to the superconvergence of local averages of the Galerkin solution.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Numerical Analysis (math.NA) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.06348 — 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 2026-10-06T05:27:06.035Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).