Non-asymptotic Identification of Linear Dynamical Systems Using Multiple Trajectories

Abstract

This paper considers the problem of linear time-invariant (LTI) system identification using input/output data. Recent work has provided non-asymptotic results on partially observed LTI system identification using a single trajectory but is only suitable for stable systems. We provide finite-time analysis for learning Markov parameters based on the ordinary least-squares (OLS) estimator using multiple trajectories, which covers both stable and unstable systems. For unstable systems, our results suggest that the Markov parameters are harder to estimate in the presence of process noise. Without process noise, our upper bound on the estimation error is independent of the spectral radius of system dynamics with high probability. These two features are different from fully observed LTI systems for which recent work has shown that unstable systems with a bigger spectral radius are easier to estimate. Extensive numerical experiments demonstrate the performance of our OLS estimator.

22 pages, 4 figures. Code for our numerical experiments is available here: https://github.com/zhengy09/SysId

References in corpus (6)

• Gradient Descent Learns Linear Dynamical Systems
• Near optimal finite time identification of arbitrary linear dynamical systems
• Improper Learning for Non-Stochastic Control
• Non-Asymptotic Analysis of Robust Control from Coarse-Grained Identification
• An Input-Output Parametrization of Stabilizing Controllers: amidst Youla and System Level Synthesis
• On the Equivalence of Youla, System-level and Input-output Parameterizations

Cited by in corpus (5)

• Near-Optimal Design of Safe Output Feedback Controllers from Noisy Data
• Non-Asymptotic State-Space Identification of Closed-Loop Stochastic Linear Systems using Instrumental Variables
• Learning the Dynamics of Autonomous Linear Systems From Multiple Trajectories
• Learning Partially Observed Linear Dynamical Systems from Logarithmic Number of Samples
• Sample Complexity of the Robust LQG Regulator with Coprime Factors Uncertainty