Skip to content
DraconiticResearch
Search Sources API
203,203 studies31 sourcesUpdated 33 min ago
PreprintCC BY 4.0arXiv

Boundary-preserving randomized neural network methods for Poisson equations on general two- and three-dimensional domains

  • Huifang Zhou
Open at sourcePDFDOICite

Abstract

In this paper, we propose a boundary-preserving randomized neural network method for Poisson equations with Dirichlet boundary conditions in two and three dimensions. A linear lifting imposes the boundary conditions exactly, without balancing penalty weights between interior and boundary residuals. We construct the liftings by generalized barycentric coordinates and transfinite interpolation on convex and nonconvex polygons and polyhedra, and by radial parameterization on star-shaped curved domains. Numerical experiments on different domains show that the proposed method substantially reduces errors compared with the standard randomized neural network method.

Related

  1. Linear ill-posedness of three-dimensional MHD boundary layer equations
    Mingxue Zhang, Zhonger Wu
    arXivPreprintarXiv licenceFull textAnalysis & PDEsarXiv
  2. Singularity Analysis of Laplace Boundary Integral Equations on Three-Dimensional Domains with Corners
    Wenmao Hua, Jun Lai, Baoling Xie +1
    arXivPreprintarXiv licenceFull textNumerical analysis & scientific computingarXiv
  3. Vanishing boundary geometry and critical pressure compactness for the three-dimensional Navier--Stokes equations
    Leyang Wang
    arXivPreprintarXiv licenceFull textAnalysis & PDEsarXiv
  4. Weak adversarial tensor neural network for high-dimensional Fokker-Planck equations
    Sihong Shao, Zhongwei Xu
    arXivPreprintarXiv licenceFull textNumerical analysis & scientific computingarXiv
  5. A support preserving homotopy for the de Rham complex with boundary decay estimates
    Andrea Nützi
    Pure and Applied AnalysisPeer-reviewedLicence not statedFull text5 citedGeneral mathematicsOpenAlex

Cite

BibTeXRIS
BibTeX
@misc{zhou2026boundarypreserving,
  title = {{Boundary-preserving randomized neural network methods for Poisson equations on general two- and three-dimensional domains}},
  author = {Huifang Zhou},
  howpublished = {arXiv},
  year = {2026},
  month = nov,
  doi = {10.48550/arxiv.2611.07985},
  eprint = {2611.07985},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2611.07985},
  note = {CC BY 4.0},
}
RIS
TY  - UNPB
TI  - Boundary-preserving randomized neural network methods for Poisson equations on general two- and three-dimensional domains
AU  - Huifang Zhou
PY  - 2026
DA  - 2026/11/05
PB  - arXiv
DO  - 10.48550/arxiv.2611.07985
UR  - https://arxiv.org/abs/2611.07985
AB  - In this paper, we propose a boundary-preserving randomized neural network method for Poisson equations with Dirichlet boundary conditions in two and three dimensions. A linear lifting imposes the boundary conditions exactly, without balancing penalty weights between interior and boundary residuals. We construct the liftings by generalized barycentric coordinates and transfinite interpolation on convex and nonconvex polygons and polyhedra, and by radial parameterization on star-shaped curved domains. Numerical experiments on different domains show that the proposed method substantially reduces errors compared with the standard randomized neural network method.
ER  -