English

Improved error bounds for Koopman operator and reconstructed trajectories approximations with kernel-based methods

Numerical Analysis 2025-11-07 v4 Numerical Analysis Dynamical Systems

Abstract

In this article, we propose a new error bound for Koopman operator approximation using Kernel Extended Dynamic Mode Decomposition. The new estimate is O(N1/2)O(N^{-1/2}), with a constant related to the probability of success of the bound, given by Hoeffding's inequality, similar to other methodologies, such as Philipp et al. Furthermore, we propose a \textit{lifting back} operator to obtain trajectories generated by embedding the initial state and iterating a linear system in a higher dimension. This naturally yields an O(N1/2)O(N^{-1/2}) error bound for mean trajectories. Finally, we show numerical results including an example of nonlinear system, exhibiting successful approximation with exponential decay faster than 1/2-1/2, as suggested by the theoretical results.

Keywords

Cite

@article{arxiv.2506.09266,
  title  = {Improved error bounds for Koopman operator and reconstructed trajectories approximations with kernel-based methods},
  author = {Diego Olguín and Axel Osses and Héctor Ramírez},
  journal= {arXiv preprint arXiv:2506.09266},
  year   = {2025}
}

Comments

24 pages, 6 figures

R2 v1 2026-07-01T03:10:17.133Z