Metraipolis › archive › dc_43a35f6aa474

Kernel Localization and Whole-Trajectory Generalization for Linear Multistep Methods in Deep Learning-Based Discovery of Dynamical Systems — arXiv:2608.08435

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.08435
License (as archived)
CC0-1.0
Archived
2026-10-19T09:07:59.366Z
SHA-256 of the archived text
375f239f430deea7db9bd41eae14b0028a507e65c14f77e3d36c0a8df54807b5
Stable URL of this page
https://metraipolis.com/documento/dc_43a35f6aa474

How to cite

Kernel Localization and Whole-Trajectory Generalization for Linear Multistep Methods in Deep Learning-Based Discovery of Dynamical Systems — arXiv:2608.08435 — arXiv (en), https://arxiv.org/abs/2608.08435 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_43a35f6aa474 (Metraipolis archive dc_43a35f6aa474, sha256 375f239f430deea7db9bd41eae14b0028a507e65c14f77e3d36c0a8df54807b5)
BibTeX
@misc{dc43a35f6aa474,
  title = {Kernel Localization and Whole-Trajectory Generalization for Linear Multistep Methods in Deep Learning-Based Discovery of Dynamical Systems — arXiv:2608.08435},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.08435},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_43a35f6aa474; sha256 375f239f430deea7db9bd41eae14b0028a507e65c14f77e3d36c0a8df54807b5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.08435. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Linear multistep methods (LMMs) combined with neural-network approximation provide a high-order framework for learning governing vector fields of dynamical systems from discrete trajectory data. This paper studies two issues in LMM-based discovery that are not resolved by existing grid-level convergence theory. First, in non-auxiliary Adams--Bashforth (A-B) and Adams--Moulton (A-M) discovery systems, we observe that zero-residual grid solutions are nonunique but consistent along the trajectory, with differences limited to the boundary layer. We explain this phenomenon through a kernel analysis of the non-auxiliary discovery matrices. Under the corresponding discovery-stability conditions, the differences between zero-residual grid solutions are exponentially localized near the initial indices for A-B schemes, whereas they form two-sided boundary layers near the initial and terminal indices for A-M schemes. Second, we derive whole-trajectory generalization estimates for both auxiliary and non-auxiliary formulations. Once the learned vector field is restricted to a fixed observed trajectory, each component of the error becomes a scalar function of time. For the auxiliary formulation, the trajectory error is $O(h^p)$ under the corresponding grid accuracy, approximation, and trace regularity assumptions. For non-auxiliary formulations, the global estimates contain additional boundary-layer terms. On fixed interior subintervals, these terms are exponentially damped. Numerical experiments illustrate the convergence behavior.

Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-08-11 in math.NA).
Categorie arXiv: Numerical Analysis (math.NA).
Pagina del lavoro: https://arxiv.org/abs/2608.08435 — 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 2026-10-19T09:05:02.956Z dalla pagina https://arxiv.org/catchup/math.NA/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).