Metraipolis › archive › dc_91dc5e14d9be

Comparison of neural and spline representations for physics-informed learning — arXiv:2610.06294

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.06294
License (as archived)
CC0-1.0
Archived
2026-10-06T13:07:15.701Z
SHA-256 of the archived text
935f5565f0c30187abd3afa5dce225c931d74e1bae67014ba509a02d850fd22d
Stable URL of this page
https://metraipolis.com/documento/dc_91dc5e14d9be

How to cite

Comparison of neural and spline representations for physics-informed learning — arXiv:2610.06294 — arXiv (en), https://arxiv.org/abs/2610.06294 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_91dc5e14d9be (Metraipolis archive dc_91dc5e14d9be, sha256 935f5565f0c30187abd3afa5dce225c931d74e1bae67014ba509a02d850fd22d)
BibTeX
@misc{dc91dc5e14d9be,
  title = {Comparison of neural and spline representations for physics-informed learning — arXiv:2610.06294},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.06294},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_91dc5e14d9be; sha256 935f5565f0c30187abd3afa5dce225c931d74e1bae67014ba509a02d850fd22d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.06294. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Physics-informed machine learning as recently emerged as a new paradigm for the resolution of partial differential equations, including functionalities for parametric modeling and inverse design, using neural networks to represent the solution fields. However, several difficulties have been reported concerning the training of such networks, resulting in slow convergence, low accurate solutions and sensitivity to the choice of hyper-parameters. In order to better understand the mechanisms underlying these difficulties, the present work proposes a rigourous comparison of neural networks and B-Splines representations within the same physics-informed learning framework. Four problems with closed-form solutions are numerically studied to establish a rigorous analysis of the accuracy and efficiency of the two representations, in terms of asymptotic convergence rates, sampling requirements, loss function minimization and arithmetic precision needed.

Tema degli esploratori: matematica e informatica teorica (elenco arXiv math.OC, nuovi lavori del giorno).
Categorie arXiv: Analysis of PDEs (math.AP) ; Numerical Analysis (math.NA); Optimization and Control (math.OC).
Pagina del lavoro: https://arxiv.org/abs/2610.06294 — 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 2026-10-06T11:21:31.944Z dalla pagina https://arxiv.org/list/math.OC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).