Metraipolis › archive › dc_52dfc3ca55de
Data-driven Koopman mode approximation: A neural power iteration algorithm — arXiv:2608.26943
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.26943
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T16:15:52.194Z
- SHA-256 of the archived text
1cc83ef9e7ba0e7090855e6967b99ec311e18b1d894093acb506a5a10eeb892f- Stable URL of this page
https://metraipolis.com/documento/dc_52dfc3ca55de
How to cite
Data-driven Koopman mode approximation: A neural power iteration algorithm — arXiv:2608.26943 — arXiv (en), https://arxiv.org/abs/2608.26943 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_52dfc3ca55de (Metraipolis archive dc_52dfc3ca55de, sha256 1cc83ef9e7ba0e7090855e6967b99ec311e18b1d894093acb506a5a10eeb892f)
BibTeX
@misc{dc52dfc3ca55de,
title = {Data-driven Koopman mode approximation: A neural power iteration algorithm — arXiv:2608.26943},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.26943},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_52dfc3ca55de; sha256 1cc83ef9e7ba0e7090855e6967b99ec311e18b1d894093acb506a5a10eeb892f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.26943. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
This paper proposes a novel data-driven algorithm to approximate the dominant eigenfunctions (aka.~modes) of the Koopman operator of nonlinear dynamical systems using neural networks. The relevance of learning the dominant Koopman modes is to approximate nonlinear dynamics by linear ones in a lifted space, thereby enabling simplified control and analysis. To fight the curse of dimensionality arising from using expressive templates (here neural networks) for the mode approximation, the proposed method leverages a power-iteration scheme that directly learns the dominant Koopman modes without explicitly constructing the projection of the Koopman operator on the template of functions. Our approach connects to other approaches in the literature that avoid the curse of dimensionality by learning small dictionaries of functions, but differs from them in that we do not require ``anti-collapse mechanisms'' to ensure that the learned dictionary is expressive enough to approximate the Koopman operator since our power-iteration scheme is designed to converge toward the dominant modes of the projected Koopman operator. The approach is fully data-driven, requiring only sampled state transitions. Theoretical guarantees are provided, showing convergence under increasing sample size and network width (in connection with the neural tangent kernel theorem). Numerical experiments demonstrate that the method achieves accurate and smooth approximations of dominant modes while avoiding the limitations of traditional techniques such as extended dynamic mode decomposition. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-28 in cs.LG). Categorie arXiv: Systems and Control (eess.SY) ; Machine Learning (cs.LG); Optimization and Control (math.OC). Pagina del lavoro: https://arxiv.org/abs/2608.26943 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T15:34:50.007Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).