A finite-sample bound for identifying partially observed linear switched systems from a single trajectory
Not on the map. Why?
Abstract (arXiv)
We derive a finite-sample probabilistic bound on the parameter estimation error of a system identification algorithm for Linear Switched Systems. The algorithm estimates Markov parameters from a single trajectory and applies a variant of the Ho-Kalman algorithm to recover the system matrices. Our bound guarantees statistical consistency under the assumption that the true system exhibits quadratic stability. The proof leverages the theory of weakly dependent processes. To the best of our knowledge, this is the first finite-sample bound for this algorithm in the single-trajectory setting.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 10 of its 29 references that are in the map. First posted on arXiv 17 Mar 2025.
Builds on
10 of 29 references.
References · 10
- 2018Learning Without Mixing: Towards A Sharp Analysis of Linear System Identificationcited by 158
- 2022Statistical Learning Theory for Control: A Finite Sample Perspectivecited by 53
- 2022Single Trajectory Nonparametric Learning of Nonlinear Dynamicscited by 26
- 2021Strong Consistency and Rate of Convergence of Switched Least Squares System Identification for Autonomous Markov Jump Linear Systemscited by 6
- 2025Finite Sample Identification of Partially Observed Bilinear Dynamical Systemscited by 5
- 2023PAC-Bayes Generalisation Bounds for Dynamical Systems Including Stable RNNscited by 4
- 2022Finite-sample analysis of identification of switched linear systems with arbitrary or restricted switchingcited by 3
- 2018Towards Efficient Maximum Likelihood Estimation of LPV-SS Modelscited by 2
- 2014Model Reduction by Moment Matching for Linear Switched Systemscited by 1
- 2024Minimal covariance realization and system identification algorithm for a class of stochastic linear switched systems with i.i.d. switchingcited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.