Metraipolis › archive › dc_fed118a43a82

Learning Physics from an Imperfect Ancestor — arXiv:2609.24947

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.24947
License (as archived)
CC0-1.0
Archived
2026-10-09T07:07:58.466Z
SHA-256 of the archived text
1fe6643d0f291b9b081f481d09955577b962af78075addeb9ff745fb3d77770b
Stable URL of this page
https://metraipolis.com/documento/dc_fed118a43a82

How to cite

Learning Physics from an Imperfect Ancestor — arXiv:2609.24947 — arXiv (en), https://arxiv.org/abs/2609.24947 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fed118a43a82 (Metraipolis archive dc_fed118a43a82, sha256 1fe6643d0f291b9b081f481d09955577b962af78075addeb9ff745fb3d77770b)
BibTeX
@misc{dcfed118a43a82,
  title = {Learning Physics from an Imperfect Ancestor — arXiv:2609.24947},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.24947},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fed118a43a82; sha256 1fe6643d0f291b9b081f481d09955577b962af78075addeb9ff745fb3d77770b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.24947. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Neural operators evaluate parametric partial differential equations cheaply but degrade sharply outside their training distribution. Physics-informed neural networks avoid dependence on labeled data, yet their optimization can be basin-fragile: when the governing residual admits multiple solutions, a PINN trained from scratch may converge to a physically incorrect state despite achieving a small residual. We show that these failure modes can be addressed jointly: an imperfect NO provides the structural prior needed to place a PINN in the correct solution basin, while the PDE residual refines the solution beyond the operator's accuracy. We introduce a three-stage framework that freezes the spatial basis of a physics-informed NO, extrapolates its solution branch to an out-of-distribution parameter using a polynomial continuation prior, and distills the resulting field into a fresh PINN. The NO need not be accurate at the target; it transfers solution-branch information, while PDE residual minimization in the PINN governs convergence. We evaluate the framework on three nonlinear PDEs: 1D viscous Burgers, 2D steady Allen-Cahn near a pitchfork bifurcation, and 2D steady lid-driven cavity flow. For Allen-Cahn, where the trivial solution satisfies the PDE residual exactly, a standard PINN collapses to the trivial zero branch, whereas distillation from the crude extrapolated operator recovers the non-trivial branch that matches the finite-difference reference. For the lid-driven cavity, extrapolating to a Reynolds number of Re = 3200 accelerates convergence to the correct physical state, achieving competitive accuracy using fewer parameters and optimization steps than recent literature baselines. These results establish a simple principle: an NO need not accurately predict the solution to be useful; it only needs to identify the correct basin from which PINN optimization can recover it.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.24947 — 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 2026-10-09T06:58:09.458Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).