Error bounds for kernel-based approximations of the Koopman operator
F. Philipp, M. Schaller, K. Worthmann, S. Peitz, F. Nüske, ArXiv:2301.08637 (2023).
Download (ext.)
Preprint
| English
Author
Philipp, Friedrich;
Schaller, Manuel;
Worthmann, Karl;
Peitz, SebastianLibreCat
;
Nüske, Feliks

Department
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.
Publishing Year
Journal Title
arXiv:2301.08637
LibreCat-ID
Cite this
Philipp F, Schaller M, Worthmann K, Peitz S, Nüske F. Error bounds for kernel-based approximations of the Koopman operator. arXiv:230108637. Published online 2023.
Philipp, F., Schaller, M., Worthmann, K., Peitz, S., & Nüske, F. (2023). Error bounds for kernel-based approximations of the Koopman operator. In arXiv:2301.08637.
@article{Philipp_Schaller_Worthmann_Peitz_Nüske_2023, title={Error bounds for kernel-based approximations of the Koopman operator}, journal={arXiv:2301.08637}, author={Philipp, Friedrich and Schaller, Manuel and Worthmann, Karl and Peitz, Sebastian and Nüske, Feliks}, year={2023} }
Philipp, Friedrich, Manuel Schaller, Karl Worthmann, Sebastian Peitz, and Feliks Nüske. “Error Bounds for Kernel-Based Approximations of the Koopman Operator.” ArXiv:2301.08637, 2023.
F. Philipp, M. Schaller, K. Worthmann, S. Peitz, and F. Nüske, “Error bounds for kernel-based approximations of the Koopman operator,” arXiv:2301.08637. 2023.
Philipp, Friedrich, et al. “Error Bounds for Kernel-Based Approximations of the Koopman Operator.” ArXiv:2301.08637, 2023.
All files available under the following license(s):
Copyright Statement:
This Item is protected by copyright and/or related rights. [...]
Link(s) to Main File(s)
Access Level
