Error bounds for kernel-based approximations of the Koopman operator

DOI10.1016/J.ACHA.2024.101657MaRDI QIDQ6423952zbMATH OpenOpenAlexFDO

Authors Friedrich Philipp, M. Schaller, Karl Worthmann, Sebastian Peitz, Feliks Nüske

Publication date 20 January 2023

Full work available at URL https://doi.org/10.1016/j.acha.2024.101657

Mathematics Subject Classification ID

Statistics (62-XX) Numerical analysis (65-XX)

Abstract: We consider the data-driven approximation of the Koopman operator for stochastic differential equations on reproducing kernel Hilbert spaces (RKHS). Our focus is on the estimation error if the data are collected from long-term ergodic simulations. We derive both an exact expression for the variance of the kernel cross-covariance operator, measured in the Hilbert-Schmidt norm, and probabilistic bounds for the finite-data estimation error. Moreover, we derive a bound on the prediction error of observables in the RKHS using a finite Mercer series expansion. Further, assuming Koopman-invariance of the RKHS, we provide bounds on the full approximation error. Numerical experiments using the Ornstein-Uhlenbeck process illustrate our results.

Cited in

(13)

• Approximation of the Koopman operator via Bernstein polynomials
• Modularized data-driven approximation of the Koopman operator and generator
• Mini-workshop: Data-driven modeling, analysis, and control of dynamical systems. Abstracts from the mini-workshop held December 8--13, 2024
• Linear quadratic control of nonlinear systems with Koopman operator learning and the Nyström method
• L^-error bounds for approximations of the Koopman operator by kernel extended dynamic mode decomposition
• Limits of learning dynamical systems
• Equivariance and partial observations in Koopman operator theory for partial differential equations
• A randomized algorithm to solve reduced rank operator regression
• SafEDMD: A Koopman-based data-driven controller design framework for nonlinear dynamical systems
• Smooth Koopman eigenfunctions
• Error analysis of kernel EDMD for prediction and control in the Koopman framework
• Koopman reduced-order modeling with confidence bounds
• Group-convolutional extended dynamic mode decomposition

This page was built for publication: Error bounds for kernel-based approximations of the Koopman operator

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6423952)