Metraipolis › archive › dc_51b0bd2e21ff
Enforcing Dirichlet Boundary Conditions in Operator Learning — arXiv:2608.27256
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.27256
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T16:15:54.705Z
- SHA-256 of the archived text
210cc30f204fa7faf36b583f8f9fca3671c322007c3b04cf3f523bfb62415221- Stable URL of this page
https://metraipolis.com/documento/dc_51b0bd2e21ff
How to cite
Enforcing Dirichlet Boundary Conditions in Operator Learning — arXiv:2608.27256 — arXiv (en), https://arxiv.org/abs/2608.27256 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_51b0bd2e21ff (Metraipolis archive dc_51b0bd2e21ff, sha256 210cc30f204fa7faf36b583f8f9fca3671c322007c3b04cf3f523bfb62415221)
BibTeX
@misc{dc51b0bd2e21ff,
title = {Enforcing Dirichlet Boundary Conditions in Operator Learning — arXiv:2608.27256},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.27256},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_51b0bd2e21ff; sha256 210cc30f204fa7faf36b583f8f9fca3671c322007c3b04cf3f523bfb62415221},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.27256. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Operator learning in scientific machine learning is concerned with approximation of maps between infinite-dimensional function spaces; such maps frequently arise as the solution operators of partial differential equations (PDEs). Neural operators have demonstrated broad empirical success at approximating such maps from data. However, most existing neural operator architectures enforce boundary conditions indirectly through training from data even though the boundary condition is often known exactly. Furthermore, existing modifications and approaches that do enforce boundary conditions explicitly suffer from impractical restrictions, including boundary smoothness, uniform grids, and separable, box-like domains. In this work, we propose an architecture which, independently of training, satisfies homogeneous Dirichlet boundary conditions, whilst simultaneously retaining the expressivity of existing kernel-integral neural operator architectures. This is achieved by enforcing the property that the output of each layer is contained in the span of a subset of the homogeneous Dirichlet eigenfunctions of the Laplacian on the output domain. The method requires only that the output domain be bounded with Lipschitz boundary and places no restriction on the choice of discretization, making it applicable to arbitrary mesh data and general geometries. We prove universal approximation for the resulting architecture; furthermore the approach we adopt in the analysis proves universality for a broad class of kernel-integral neural operators thereby uniting existing theory for a variety of operator learning methods. We validate the proposed method on maps defined by the coefficient to solution map in 2D PDEs: Darcy flow on a square domain and the Helmholtz equation on a circular domain. Comparisons are made with alternative methods. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-28 in cs.LG). Categorie arXiv: Numerical Analysis (math.NA) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.27256 — 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 2026-10-17T15:34:50.016Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).