Closed-loop Parameter Identification of Linear Dynamical Systems through the Lens of Feedback Channel Coding Theory
This work addresses the fundamental limitations of parameter learning in control systems, providing theoretical insights for researchers in system identification and control theory, though it is incremental in connecting identification to channel coding.
The paper tackles the problem of closed-loop identification of linear scalar systems with Gaussian noise, establishing a fundamental upper bound on the learning rate equal to the capacity of an AWGN channel and proving that super-linear convergence is unattainable.
This paper considers the problem of closed-loop identification of linear scalar systems with Gaussian process noise, where the system input is determined by a deterministic state feedback policy. The regularized least-square estimate (LSE) algorithm is adopted, seeking to find the best estimate of unknown model parameters based on noiseless measurements of the state. We are interested in the fundamental limitation of the rate at which unknown parameters can be learned, in the sense of the D-optimality scalarization criterion subject to a quadratic control cost. We first establish a novel connection between a closed-loop identification problem of interest and a channel coding problem involving an additive white Gaussian noise (AWGN) channel with feedback and a certain structural constraint. Based on this connection, we show that the learning rate is fundamentally upper bounded by the capacity of the corresponding AWGN channel. Although the optimal design of the feedback policy remains challenging, we derive conditions under which the upper bound is achieved. Finally, we show that the obtained upper bound implies that super-linear convergence is unattainable for any choice of the policy.