Metraipolis › archive › dc_21bc2ab3e46b

Selective boundary condition reduction via learned error gating — arXiv:2609.08461

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.08461
License (as archived)
CC0-1.0
Archived
2026-10-16T13:59:36.239Z
SHA-256 of the archived text
f8473db3fe22c19aafaaa5e6fefe5a26dd21129b9f786df3a412ac278b8b0e7e
Stable URL of this page
https://metraipolis.com/documento/dc_21bc2ab3e46b

How to cite

Selective boundary condition reduction via learned error gating — arXiv:2609.08461 — arXiv (en), https://arxiv.org/abs/2609.08461 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_21bc2ab3e46b (Metraipolis archive dc_21bc2ab3e46b, sha256 f8473db3fe22c19aafaaa5e6fefe5a26dd21129b9f786df3a412ac278b8b0e7e)
BibTeX
@misc{dc21bc2ab3e46b,
  title = {Selective boundary condition reduction via learned error gating — arXiv:2609.08461},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.08461},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_21bc2ab3e46b; sha256 f8473db3fe22c19aafaaa5e6fefe5a26dd21129b9f786df3a412ac278b8b0e7e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.08461. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Parametric PDEs can admit different boundary conditions with different accuracy and computational cost. We introduce a framework for learning when one reduced boundary condition can replace another: paired solutions train a neural network to estimate the resulting domain and boundary errors, and the simpler condition is used only when both predicted errors meet prescribed tolerances. We focus on singular limits in applications, in which a stiff Robin or nonlinear boundary law is replaced by its limiting Dirichlet form. We evaluate the method on a galvanic corrosion problem and other nonlinear stationary and evolution problems.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.LG).
Categorie arXiv: Numerical Analysis (math.NA) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.08461 — 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 2026-10-16T13:39:43.279Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).