Strong Consistency and Rate of Convergence of Switched Least Squares System Identification for Autonomous Markov Jump Linear Systems
This work addresses system identification for Markov jump linear systems, offering a weaker stability assumption and matching convergence rates, but it is incremental as it extends existing least squares methods to a more complex setting.
The paper tackles system identification for autonomous Markov jump linear systems with complete state observations by proposing a switched least squares method, proving its strong consistency and deriving an almost sure convergence rate of O(sqrt(log(T)/T)), matching that of least squares for linear systems.
In this paper, we investigate the problem of system identification for autonomous Markov jump linear systems (MJS) with complete state observations. We propose switched least squares method for identification of MJS, show that this method is strongly consistent, and derive data-dependent and data-independent rates of convergence. In particular, our data-independent rate of convergence shows that, almost surely, the system identification error is $\mathcal{O}\big(\sqrt{\log(T)/T} \big)$ where $T$ is the time horizon. These results show that switched least squares method for MJS has the same rate of convergence as least squares method for autonomous linear systems. We derive our results by imposing a general stability assumption on the model called stability in the average sense. We show that stability in the average sense is a weaker form of stability compared to the stability assumptions commonly imposed in the literature. We present numerical examples to illustrate the performance of the proposed method.