Metraipolis › archive › dc_dcb9391a1007
Checkable NTK Positivity and Finite-Width Gradient Descent for Scalar- and Vector-Valued PINNs with Strong-Form, Weak-Form, and Nonlocal Linear Constraints — arXiv:2610.04357
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.04357
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:30:32.100Z
- SHA-256 of the archived text
c21f59dbe0b78adbef6780b94b768a310dd50004fd23465401d09f1c7700fd34- Stable URL of this page
https://metraipolis.com/documento/dc_dcb9391a1007
How to cite
Checkable NTK Positivity and Finite-Width Gradient Descent for Scalar- and Vector-Valued PINNs with Strong-Form, Weak-Form, and Nonlocal Linear Constraints — arXiv:2610.04357 — arXiv, https://arxiv.org/abs/2610.04357 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dcb9391a1007 (Metraipolis archive dc_dcb9391a1007, sha256 c21f59dbe0b78adbef6780b94b768a310dd50004fd23465401d09f1c7700fd34)
BibTeX
@misc{dcdcb9391a1007,
title = {Checkable NTK Positivity and Finite-Width Gradient Descent for Scalar- and Vector-Valued PINNs with Strong-Form, Weak-Form, and Nonlocal Linear Constraints — arXiv:2610.04357},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.04357},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dcb9391a1007; sha256 c21f59dbe0b78adbef6780b94b768a310dd50004fd23465401d09f1c7700fd34},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.04357. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We give checkable positive-definiteness criteria for the limiting neural tangent kernel (NTK) and high-probability finite-width gradient-descent guarantees for scalar- or vector-valued physics-informed neural networks (PINNs) with linear constraints. The constraints may be strong-form differential rows of any fixed finite order, including coupled systems, with any linear initial or boundary conditions; weak-form residual and boundary functionals; or finite-measure nonlocal observations such as integral, nonlocal-diffusion, and Dirac-data rows, all in any dimension. For each class, positive definiteness of the limiting NTK is equivalent to a rank condition on a finite coefficient, functional, or moment matrix of the fixed design: a certificate computed before training that detects structural zero modes. The model hypotheses are those of an ordinary two-layer PINN, a smooth nonpolynomial activation with bounded symmetric initialization, and are met by standard choices such as $\tanh$ with uniform initialization. Given a certificate, explicit width and step-size conditions ensure, with high probability, that the empirical NTK retains at least half the limiting gap and that full-batch gradient descent decreases the training loss geometrically at every iteration. Controlled experiments check the certificates and the finite-width mechanism. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Numerical Analysis (math.NA). Pagina del lavoro: https://arxiv.org/abs/2610.04357 — 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 2026-10-06T05:27:05.676Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).