Abstract:We consider federated learning of linearly-parameterized nonlinear systems. We establish theoretical guarantees on the effectiveness of federated nonlinear system identification compared to centralized approaches, demonstrating that the convergence rate improves as the number of clients increases. Although the convergence rates in the linear and nonlinear cases differ only by a constant, this constant depends on the feature map $\phi$, which can be carefully chosen in the nonlinear setting to increase excitation and improve performance. We experimentally validate our theory in physical settings where client devices are driven by i.i.d. control inputs and control policies exhibiting i.i.d. random perturbations, ensuring non-active exploration. Experiments use trajectories from nonlinear dynamical systems characterized by real-analytic feature functions, including polynomial and trigonometric components, representative of physical systems including pendulum and quadrotor dynamics. We analyze the convergence behavior of the proposed method under varying noise levels and data distributions. Results show that federated learning consistently improves convergence of any individual client as the number of participating clients increases.
| Comments: | Accepted at American Control Conference 2026 |
| Subjects: | Machine Learning (cs.LG); Systems and Control (eess.SY) |
| Cite as: | arXiv:2508.15025 [cs.LG] |
| (or arXiv:2508.15025v5 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2508.15025 arXiv-issued DOI via DataCite |
From: Omkar Tanaji Tupe [view email]
[v1]
Wed, 20 Aug 2025 19:41:43 UTC (1,021 KB)
[v2]
Sun, 24 Aug 2025 18:27:30 UTC (1,021 KB)
[v3]
Fri, 27 Feb 2026 10:30:26 UTC (2,584 KB)
[v4]
Mon, 2 Mar 2026 10:20:35 UTC (2,584 KB)
[v5]
Fri, 24 Apr 2026 07:10:41 UTC (2,673 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。