Metraipolis › archive › dc_5bec90d45cfd

The Symbol of the Surrogate: Measuring Numerical Provenance in Neural PDE Solvers — arXiv:2610.09255

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.09255
License (as archived)
CC0-1.0
Archived
2026-10-08T11:56:32.055Z
SHA-256 of the archived text
7eeaca4e4f833b5805fe5d80c7c4e22775e7529c7aee6962035243d912c2e160
Stable URL of this page
https://metraipolis.com/documento/dc_5bec90d45cfd

How to cite

The Symbol of the Surrogate: Measuring Numerical Provenance in Neural PDE Solvers — arXiv:2610.09255 — arXiv (en), https://arxiv.org/abs/2610.09255 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5bec90d45cfd (Metraipolis archive dc_5bec90d45cfd, sha256 7eeaca4e4f833b5805fe5d80c7c4e22775e7529c7aee6962035243d912c2e160)
BibTeX
@misc{dc5bec90d45cfd,
  title = {The Symbol of the Surrogate: Measuring Numerical Provenance in Neural PDE Solvers — arXiv:2610.09255},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.09255},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5bec90d45cfd; sha256 7eeaca4e4f833b5805fe5d80c7c4e22775e7529c7aee6962035243d912c2e160},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.09255. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Neural PDE surrogates are trained on numerical solver outputs that contain both physical evolution and solver-specific discretization errors. Because surrogates are also evaluated against held-out trajectories from the same solver, standard benchmarks cannot distinguish fidelity to the exact evolution from imitation of the numerical scheme. We introduce an empirical Fourier-symbol diagnostic that probes a trained surrogate's linearized one-step operator with individual Fourier modes and compares it with both exact-evolution and training-scheme references. To address architectural spectral bias, we train identical networks on schemes with orthogonal dissipative and dispersive signatures and compare their learned operators. In linear advection, the learned surrogates reproduce the training schemes' amplitude and phase errors, with the twin-scheme difference reaching more than 99.8\% of the analytically predicted full-imitation ceiling. The same behavior occurs for a non-local Fourier neural operator and at the operator level for nonlinear Burgers dynamics. These results show that agreement with solver-generated test data does not by itself establish fidelity to the exact evolution. Fourier-symbol measurements provide a direct diagnostic of numerical provenance.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Analysis of PDEs (math.AP); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2610.09255 — 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 2026-10-08T10:50:37.672Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).