Spatio-Temporal Prediction via Operator-Valued RKHS and Koopman Approximation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Withanachchi, Mahishanka
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915999432835072
author Withanachchi, Mahishanka
author_facet Withanachchi, Mahishanka
contents We develop a comprehensive framework for spatio-temporal prediction of time-varying vector fields using operator-valued reproducing kernel Hilbert spaces (OV RKHS). By integrating Sobolev regularity with Koopman operator theory, we establish representer theorems, approximation rates, and spectral convergence results for kernel-based learning of dynamical systems. Our theoretical contributions include new representer theorems for time-aligned OV RKHS interpolation, Sobolev approximation bounds for smooth vector fields, kernel Koopman operator approximations, and spectral convergence guarantees. These results underpin data-driven reduced-order modeling and forecasting for complex nonlinear dynamical systems.
format Preprint
id arxiv_https___arxiv_org_abs_2507_12474
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Spatio-Temporal Prediction via Operator-Valued RKHS and Koopman Approximation
Withanachchi, Mahishanka
General Mathematics
We develop a comprehensive framework for spatio-temporal prediction of time-varying vector fields using operator-valued reproducing kernel Hilbert spaces (OV RKHS). By integrating Sobolev regularity with Koopman operator theory, we establish representer theorems, approximation rates, and spectral convergence results for kernel-based learning of dynamical systems. Our theoretical contributions include new representer theorems for time-aligned OV RKHS interpolation, Sobolev approximation bounds for smooth vector fields, kernel Koopman operator approximations, and spectral convergence guarantees. These results underpin data-driven reduced-order modeling and forecasting for complex nonlinear dynamical systems.
title Spatio-Temporal Prediction via Operator-Valued RKHS and Koopman Approximation
topic General Mathematics
url https://arxiv.org/abs/2507.12474