Metraipolis › archive › dc_c3f58f14b4fa

PE-EK-PINN: Physics Embedding with Evolving Kernel for Scalable Physics-Informed Neural Networks — arXiv:2609.38023

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.38023
License (as archived)
CC0-1.0
Archived
2026-10-07T16:24:25.520Z
SHA-256 of the archived text
6109e4075f185578dea8345256efbef36bf62e2b0ff0bb90a7d8ea7c683a7040
Stable URL of this page
https://metraipolis.com/documento/dc_c3f58f14b4fa

How to cite

PE-EK-PINN: Physics Embedding with Evolving Kernel for Scalable Physics-Informed Neural Networks — arXiv:2609.38023 — arXiv (en), https://arxiv.org/abs/2609.38023 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c3f58f14b4fa (Metraipolis archive dc_c3f58f14b4fa, sha256 6109e4075f185578dea8345256efbef36bf62e2b0ff0bb90a7d8ea7c683a7040)
BibTeX
@misc{dcc3f58f14b4fa,
  title = {PE-EK-PINN: Physics Embedding with Evolving Kernel for Scalable Physics-Informed Neural Networks — arXiv:2609.38023},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.38023},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c3f58f14b4fa; sha256 6109e4075f185578dea8345256efbef36bf62e2b0ff0bb90a7d8ea7c683a7040},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38023. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Physics-Informed Neural Networks (PINNs) embed governing equations into deep learning, but enforce them only through loss residuals, leaving highly oscillatory wave behavior to be discovered by optimization. As a result, methods that achieve relative $L_2$ errors below $10^{-3}$ on standard manufactured Helmholtz benchmarks can fail on practical radiation problems involving singular excitations, absorbing boundaries, and wave fields spanning tens of wavelengths. Architectural physics embedding addresses this limitation by factorizing the field into analytically derived oscillatory kernels and learnable envelopes. However, the kernel dictionary must be manually constructed and scales with the number of elementary units, growing exponentially with the depth of hierarchically structured systems such as antenna arrays and metasurfaces. We propose PE-EK-PINN (Physics Embedded with Evolving Kernels), which treats physics kernels as reusable learned representations rather than fixed analytical inputs. A converged subsystem field is frozen and promoted to an evolved kernel, whose transformed copies are reused to represent higher-level configurations without deriving new governing equations. The resulting hierarchy makes the peak number of active kernels independent of system size and reduces cumulative training cost from $O(N)$ to $O(\log N)$. Experiments on dipole arrays, composite line-source geometries, and cross arrays demonstrate the dramatic training cost reduction, while achieving a reduced or comparable relative $L_2$ error. One notable example is PE-EK-PINN solves a $256$-dipole array more than 30 times faster than direct PE-PINN.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.38023 — 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 2026-10-07T15:54:53.683Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).