Spectral Flow Learning Theory: Finite-Sample Guarantees for Vector-Field Identification

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Leung, Chi Ho, Paré, Philip E.
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866918425922633728
author Leung, Chi Ho
Paré, Philip E.
author_facet Leung, Chi Ho
Paré, Philip E.
contents We study the identification of continuous-time vector fields from irregularly sampled trajectories. We introduce spectral flow learning, which learns in a windowed flow space using a lag-linear label operator that aggregates lagged Koopman actions. We provide finite-sample, high-probability (FS-HP) guarantees for the class of variable-step linear multistep methods (vLMM). The FS-HP rates are constructed using spectral regularization with qualification-controlled filters for flow predictors under standard source and filter assumptions. A multistep observability inequality links flow error to vector-field error and yields two-term bounds that combine a statistical rate with an explicit discretization bias from vLMM theory. Simulations on a controlled mass-spring system corroborate the theory and clarify conditioning, step-sample tradeoffs, and practical implications.
format Preprint
id arxiv_https___arxiv_org_abs_2509_25000
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Spectral Flow Learning Theory: Finite-Sample Guarantees for Vector-Field Identification
Leung, Chi Ho
Paré, Philip E.
Systems and Control
We study the identification of continuous-time vector fields from irregularly sampled trajectories. We introduce spectral flow learning, which learns in a windowed flow space using a lag-linear label operator that aggregates lagged Koopman actions. We provide finite-sample, high-probability (FS-HP) guarantees for the class of variable-step linear multistep methods (vLMM). The FS-HP rates are constructed using spectral regularization with qualification-controlled filters for flow predictors under standard source and filter assumptions. A multistep observability inequality links flow error to vector-field error and yields two-term bounds that combine a statistical rate with an explicit discretization bias from vLMM theory. Simulations on a controlled mass-spring system corroborate the theory and clarify conditioning, step-sample tradeoffs, and practical implications.
title Spectral Flow Learning Theory: Finite-Sample Guarantees for Vector-Field Identification
topic Systems and Control
url https://arxiv.org/abs/2509.25000