Metraipolis › archive › dc_de8d65ec8d29

Function-Space Certification for Neural Operators — arXiv:2611.09038

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.09038
License (as archived)
CC0-1.0
Archived
2026-11-09T22:41:23.909Z
SHA-256 of the archived text
57ac8876a449663b23474454aa932c11497e6aabafae4afc33eba718484fed41
Stable URL of this page
https://metraipolis.com/documento/dc_de8d65ec8d29

How to cite

Function-Space Certification for Neural Operators — arXiv:2611.09038 — arXiv (en), https://arxiv.org/abs/2611.09038 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_de8d65ec8d29 (Metraipolis archive dc_de8d65ec8d29, sha256 57ac8876a449663b23474454aa932c11497e6aabafae4afc33eba718484fed41)
BibTeX
@misc{dcde8d65ec8d29,
  title = {Function-Space Certification for Neural Operators — arXiv:2611.09038},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.09038},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_de8d65ec8d29; sha256 57ac8876a449663b23474454aa932c11497e6aabafae4afc33eba718484fed41},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.09038. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Certifying the robustness and physical consistency of scientific machine-learning models ensures that their predictions remain reliable beyond the test set. For neural operators, which learn PDE solution operators by mapping infinite-dimensional function spaces, certification means establishing rigorous, domain-wide guarantees for their output functions. However, standard neural network (NN) verification methods are fundamentally designed for vector-to-vector mappings, and they can only certify neural operators at fixed grid resolutions and provide no guarantees over the entire domain or across another resolution. We close this gap by introducing a function-space certification framework that verifies neural operators across the entire continuous domain. We formulate interval bound propagation (IBP) and CROWN in function space, propagating upper and lower bound functions through each layer using rigorous numerical integration. In addition, we extend bound propagation to higher-order derivatives to certify PDE residuals and solution error bounds. Experiments across several neural operator architectures and scientific problems, including the 572.5-million-parameter spherical Fourier neural operator for global weather forecasting, show that our method produces tight, domain-wide guarantees efficiently, providing a foundation for trustworthy operator learning.

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/2611.09038 — 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 2026-11-09T22:33:47.150Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).