Statistical Consistency of Set-Membership Estimator for Linear Systems

Abstract

Suppose we can choose from a set of linear autonomous systems with bounded process noise, the dynamics of each system are unknown, and we would like to design a stabilizing policy. The underlying question is how to estimate the dynamics of each system given that measurements of each system will be nonsequential. Though seemingly straightforward, existing proof techniques for proving statistical consistency of system identification procedures fail when measurements are nonsequential. Here, we prove that the set-membership estimator is statistically consistent even when measurements are nonsequential. We numerically illustrate its strong consistency.

References in corpus (5)

• Order determination in general vector autoregressions
• Asymptotic theory of least squares estimators for nearly unstable processes under strong dependence
• Online Least Squares Estimation with Self-Normalized Processes: An Application to Bandit Problems
• Learning-based Control of Unknown Linear Systems with Thompson Sampling
• Learning Linear Dynamical Systems with Semi-Parametric Least Squares