Metraipolis › archive › dc_bd037e32a6bc

Error Analysis for Solving Elliptic Interface Problems with Randomized Neural Networks — arXiv:2609.26534

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.26534
License (as archived)
CC0-1.0
Archived
2026-10-08T15:55:32.509Z
SHA-256 of the archived text
a0d8deba08908b3fc5a6bc00bb76f5a95cccfb558b7bf2ecd4fd0e736313063d
Stable URL of this page
https://metraipolis.com/documento/dc_bd037e32a6bc

How to cite

Error Analysis for Solving Elliptic Interface Problems with Randomized Neural Networks — arXiv:2609.26534 — arXiv (en), https://arxiv.org/abs/2609.26534 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bd037e32a6bc (Metraipolis archive dc_bd037e32a6bc, sha256 a0d8deba08908b3fc5a6bc00bb76f5a95cccfb558b7bf2ecd4fd0e736313063d)
BibTeX
@misc{dcbd037e32a6bc,
  title = {Error Analysis for Solving Elliptic Interface Problems with Randomized Neural Networks — arXiv:2609.26534},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.26534},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bd037e32a6bc; sha256 a0d8deba08908b3fc5a6bc00bb76f5a95cccfb558b7bf2ecd4fd0e736313063d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.26534. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

This paper presents a unified error analysis of randomized neural networks (RaNNs) for elliptic interface problems. We first derive an integral representation of Barron functions using the standard $\tanh$ activation, which yields a $C^2$-approximation bound valid for any hidden-parameter distribution supported on a cube with strictly positive density. We then establish a quantitative $\mathcal{O}(n^{-1})$ generalization bound for the composite loss that enforces the partial differential equation, boundary, and interface conditions simultaneously, where $n$ denotes the number of training samples. Combining these results with the optimization guarantees for RaNNs, we obtain an a priori $L^2$ error estimate for the neural network solution in the presence of interface discontinuities. Numerical experiments are presented to validate the theoretical results.

Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-09-23 in math.NA).
Categorie arXiv: Numerical Analysis (math.NA).
Pagina del lavoro: https://arxiv.org/abs/2609.26534 — 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 2026-10-08T15:15:47.523Z dalla pagina https://arxiv.org/catchup/math.NA/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).