2000 character limit reached
$L^\infty$-error bounds for approximations of the Koopman operator by kernel extended dynamic mode decomposition (2403.18809v2)
Published 27 Mar 2024 in math.DS, cs.NA, and math.NA
Abstract: Extended dynamic mode decomposition (EDMD) is a well-established method to generate a data-driven approximation of the Koopman operator for analysis and prediction of nonlinear dynamical systems. Recently, kernel EDMD (kEDMD) has gained popularity due to its ability to resolve the challenging task of choosing a suitable dictionary by using the kernel's canonical features and, thus, data-informed observables. In this paper, we provide the first pointwise bounds on the approximation error of kEDMD. The main idea consists of two steps. First, we show that the reproducing kernel Hilbert spaces of Wendland functions are invariant under the Koopman operator. Second, exploiting that the learning problem given by regression in the native norm can be recast as an interpolation problem, we prove our novel error bounds by using interpolation estimates. Finally, we validate our findings with numerical experiments.
- Robert A Adams and John J F Fournier. Sobolev spaces, volume 140. Elsevier/Academic Press, Amsterdam, second edition, 2003.
- Forecasting sequential data using consistent Koopman autoencoders. In International Conference on Machine Learning, pages 475–485. PMLR, 2020.
- The Mathematical Theory of Finite Element Methods. Springer New York, 2008.
- Extracting spatial–temporal coherent patterns in large-scale neural recordings using dynamic mode decomposition. Journal of Neuroscience Methods, 258:1–15, 2016.
- Modern Koopman Theory for Dynamical Systems. SIAM Review, 64(2):229–340, 2022.
- Interpolation of Hilbert and Sobolev spaces: quantitative estimates and counterexamples. Mathematika, 61:414–443, 2015.
- Beyond expectations: residual dynamic mode decomposition and variance for stochastic dynamical systems. Nonlinear Dynamics, 112:2037–2061, 2024.
- Optimizing neural networks via Koopman operator theory. Advances in Neural Information Processing Systems, 33:2087–2097, 2020.
- GE Fasshauer. Meshfree methods. Handbook of Theoretical and Computational Nanotechnology, 27:33–97, 2005.
- Koopman analysis of the long-term evolution in a turbulent convection cell. Journal of Fluid Mechanics, 847:735–767, 2018.
- Homeomorphisms that induce monomorphisms of Sobolev spaces. Israel Journal of Mathematics, 91:31–60, 1995.
- The kernel perspective on dynamic mode decomposition. Preprint, arxiv:2106.00106, 2023.
- M Hegland and J T Marti. Numerical computation of least constants for the Sobolev inequality. Numerische Mathematik, 48(6):607–616, November 1986.
- Warren Johnson. The curious history of Faa di Bruno’s formula. American Mathematical Monthly, 109:217–234, 03 2002.
- Kernel-based approximation of the Koopman generator and Schrödinger operator. Entropy, 22(7):722, 2020.
- B O Koopman. Hamiltonian systems and transformation in Hilbert space. Proceedings of the National Academy of Sciences of the United States of America, 17:315, 1931.
- On convergence of extended dynamic mode decomposition to the Koopman operator. J. Nonlinear Science, 28(2):687–710, 2018.
- W McLean. Strongly Elliptic Systems and Boundary Integral Equations. Cambridge University Press, 2000.
- I. Mezić. On numerical approximations of the Koopman operator. Mathematics, 10:1180, 2022.
- Igor Mezić. Spectral properties of dynamical systems, model reduction and decompositions. Nonlinear Dynamics, 41(1-3):309–325, 2005.
- Igor Mezić. Analysis of fluid flows via spectral properties of the Koopman operator. Annual Review of Fluid Mechanics, 45:357–378, 2013.
- Finite-data error bounds for Koopman-based prediction and control. Journal of Nonlinear Science, 33:14, 2023.
- V I Paulsen and M Raghupathi. An Introduction to the Theory of Reproducing Kernel Hilbert Spaces. Cambridge University Press, 2016.
- Extended dynamic mode decomposition: Sharp bounds on the sample efficiency. Preprint, arXiv:2402.02494, 2024.
- Error analysis of kernel EDMD for prediction and control in the Koopman framework. Preprint, arxiv:2312.10460, 2023.
- Error bounds for kernel-based approximations of the Koopman operator. Preprint, arxiv:2301.08637, 2023.
- Towards reliable data-based optimal and predictive control using extended DMD. IFAC-PapersOnLine, 56(1):169–174, 2023.
- I Steinwart and A Christmann. Support Vector Machines. Springer Science+Business Media, LLC, 2008.
- Luc Tartar. An Introduction to Sobolev Spaces and Interpolation Spaces (Lecture Notes of the Unione Matematica Italiana). Springer, 2007.
- Holger Wendland. Scattered data approximation, volume 17. Cambridge university press, 2004.
- A kernel-based method for data-driven Koopman spectral analysis. Journal of Computational Dynamics, 2:247–265, 2015.
- Variational Koopman models: Slow collective variables and molecular kinetics from short off-equilibrium simulations. The Journal of Chemical Physics, 146(15), 2017.
- Approximation of the Koopman operator via bernstein polynomials. arXiv preprint arXiv:2403.02438, 2024.
- C. Zhang and E. Zuazua. A quantitative analysis of Koopman operator methods for system identification and predictions. Comptes Rendus Mécanique, 351:1–31, 2023.