当前位置: X-MOL 学术Appl. Comput. Harmon. Anal. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Error bounds for kernel-based approximations of the Koopman operator
Applied and Computational Harmonic Analysis ( IF 2.6 ) Pub Date : 2024-04-04 , DOI: 10.1016/j.acha.2024.101657
Friedrich M. Philipp , Manuel Schaller , Karl Worthmann , Sebastian Peitz , Feliks Nüske

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.

中文翻译:

Koopman 算子基于核的近似的误差界限

我们考虑再生核希尔伯特空间(RKHS)上随机微分方程的库普曼算子的数据驱动近似。如果数据是从长期遍历模拟中收集的,我们的重点是估计误差。我们推导了以希尔伯特-施密特范数测量的核互协方差算子方差的精确表达式,以及有限数据估计误差的概率界限。此外,我们使用有限 Mercer 级数展开推导了 RKHS 中可观测量预测误差的界限。此外,假设 RKHS 具有库普曼不变性,我们提供了完全近似误差的界限。使用 Ornstein-Uhlenbeck 过程的数值实验说明了我们的结果。
更新日期:2024-04-04
down
wechat
bug