Metraipolis › archive › dc_ff64fe133e7d
Learning Lyapunov Operators for Nonlinear Systems — arXiv:2609.18894
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.18894
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T15:08:10.617Z
- SHA-256 of the archived text
70502246d81a1707a593e3c76dc31614033e7eda54dbd91e59f45df14f137469- Stable URL of this page
https://metraipolis.com/documento/dc_ff64fe133e7d
How to cite
Learning Lyapunov Operators for Nonlinear Systems — arXiv:2609.18894 — arXiv (en), https://arxiv.org/abs/2609.18894 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ff64fe133e7d (Metraipolis archive dc_ff64fe133e7d, sha256 70502246d81a1707a593e3c76dc31614033e7eda54dbd91e59f45df14f137469)
BibTeX
@misc{dcff64fe133e7d,
title = {Learning Lyapunov Operators for Nonlinear Systems — arXiv:2609.18894},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.18894},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ff64fe133e7d; sha256 70502246d81a1707a593e3c76dc31614033e7eda54dbd91e59f45df14f137469},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.18894. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Constructing Lyapunov functions for nonlinear dynamical systems is a central problem in stability analysis, yet remains challenging. Lyapunov functions are commonly characterized as solutions to first-order partial differential equations (PDEs), but these solutions are typically obtained for single systems, limiting their reuse across systems. In this paper, we study the Lyapunov solution operator that maps a vector field to the corresponding Lyapunov function defined by a dissipation-based Lyapunov PDE. We establish that, on compact subsets of the domain of attraction and under exponential stability assumptions, this operator is well-defined, unique, and continuous with respect to perturbations of both the vector field and the dissipation function. These results provide a theoretical foundation for approximating Lyapunov functions uniformly over families of nonlinear systems. Building on these theoretical foundations, we employ Fourier Neural Operators (FNOs) as a data-driven approximation of the Lyapunov solution operator. Numerical experiments demonstrate that a single trained operator can accurately approximate the numerical Lyapunov functions across parameterized families of dynamics. This illustrates the potential of neural operators for approximating Lyapunov functions. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-17 in cs.LG). Categorie arXiv: Analysis of PDEs (math.AP) ; Machine Learning (cs.LG); Optimization and Control (math.OC). Pagina del lavoro: https://arxiv.org/abs/2609.18894 — 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 2026-10-15T14:08:19.283Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).