Metraipolis › archive › dc_09cf76529f6c

Low-Fidelity FDM Spectral Guidance for Neural Eigenvalue Solvers — arXiv:2610.04695

Source
arXiv
Original
https://arxiv.org/abs/2610.04695
License (as archived)
CC0-1.0
Archived
2026-10-06T05:30:41.211Z
SHA-256 of the archived text
090199ba487cee4511873fba66f562440665a380682f03ad60d2834212b7cd8d
Stable URL of this page
https://metraipolis.com/documento/dc_09cf76529f6c

How to cite

Low-Fidelity FDM Spectral Guidance for Neural Eigenvalue Solvers — arXiv:2610.04695 — arXiv, https://arxiv.org/abs/2610.04695 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_09cf76529f6c (Metraipolis archive dc_09cf76529f6c, sha256 090199ba487cee4511873fba66f562440665a380682f03ad60d2834212b7cd8d)
BibTeX
@misc{dc09cf76529f6c,
  title = {Low-Fidelity FDM Spectral Guidance for Neural Eigenvalue Solvers — arXiv:2610.04695},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.04695},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_09cf76529f6c; sha256 090199ba487cee4511873fba66f562440665a380682f03ad60d2834212b7cd8d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.04695. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Operator eigenvalue problems appear throughout science. Classical methods usually discretize the operator into a matrix and then solve the resulting matrix eigenvalue problem. This works well in low dimensions, but fine grids quickly become expensive in both memory and computation as the dimension grows. Neural network based solvers avoid storing these large grids, but recent state of the art neural methods can require hundreds of thousands of training steps and may struggle to find the desired eigenvalues. We show that the two approaches can help each other. A coarse finite difference method (FDM) calculation acts as a cheap numerical model of the operator spectrum. We use the approximate eigenvalues as fixed shifts during the training of the neural solver, as they only need to locate the relevant part of the spectrum. We also introduce Stabilized Inverse Power Method Neural Network (SIPMNN), a more stable training procedure for higher-dimensional problems. Across five test problems at $d=10$, the combined approach is more accurate overall than the tested fully neural alternatives while using eight to ten times fewer iterations.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.04695 — 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 2026-10-06T05:27:05.709Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).