Metraipolis › archive › dc_738fdf2170c5
Convergence of kernel and neural-network methods for Hamilton--Jacobi--Bellman equations on unbounded domains — arXiv:2610.09299
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.09299
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T12:43:35.625Z
- SHA-256 of the archived text
72a256377860684501d39f1890d6fde622566e4b8eeac68e4b7594dc856c2a7b- Stable URL of this page
https://metraipolis.com/documento/dc_738fdf2170c5
How to cite
Convergence of kernel and neural-network methods for Hamilton--Jacobi--Bellman equations on unbounded domains — arXiv:2610.09299 — arXiv (en), https://arxiv.org/abs/2610.09299 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_738fdf2170c5 (Metraipolis archive dc_738fdf2170c5, sha256 72a256377860684501d39f1890d6fde622566e4b8eeac68e4b7594dc856c2a7b)
BibTeX
@misc{dc738fdf2170c5,
title = {Convergence of kernel and neural-network methods for Hamilton--Jacobi--Bellman equations on unbounded domains — arXiv:2610.09299},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.09299},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_738fdf2170c5; sha256 72a256377860684501d39f1890d6fde622566e4b8eeac68e4b7594dc856c2a7b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.09299. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We derive error bounds from empirical squared residuals for two non-monotone, mesh-free approximations of Hamilton--Jacobi--Bellman equations on unbounded spatial domains: collocation with Wendland kernels under a native space norm constraint, and physics-informed neural networks with smooth activations under a Sobolev-norm constraint. The main step is to recover the pointwise residual control needed for viscosity-solution error estimates from the empirical loss, while quantifying the discretization or sampling error. For the kernel method, we prove uniform convergence on compact sets under classical and native space regularity and derive an a posteriori quantitative error bound for the unique bounded continuous viscosity solution. For the neural-network method, we prove uniform convergence on compact sets in probability and give a quantitative high-probability error bound under classical Sobolev regularity. The bounds are governed by the fill distance for kernels and by the network and sample sizes for neural networks. The proofs combine empirical-to-population estimates, an interpolation inequality that turns an $L^2$ residual into a sup norm bound, and a controlled diffusion estimate for the error caused by truncating the domain. The regularity assumptions used to obtain convergence from approximation properties are additional to viscosity wellposedness. Numerical experiments in one and two space dimensions illustrate the methods and the estimates. Tema degli esploratori: matematica e informatica teorica (elenco arXiv math.NA, nuovi lavori del giorno). Categorie arXiv: Numerical Analysis (math.NA). Pagina del lavoro: https://arxiv.org/abs/2610.09299 — 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 2026-10-08T12:16:45.205Z dalla pagina https://arxiv.org/list/math.NA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).