Learning Theory Approach to a System Identification Problem Involving Atomic Norm

This paper aims at proposing a learning theory approach to the topic of estimating transfer functions in system identification. A frequency domain identification problem is formulated as an atomic norm regularization scheme in a random design framework of learning theory. Such a formulation makes it possible to obtain sparsity and provide finite sample estimates for learning the transfer function in a learning theory framework. Error analysis is done for the learning algorithm by applying a local polynomial reproduction formula, concentration inequalities and iteration techniques. The convergence rate obtained here is the best in the literature. It is hoped that the learning theory approach to the frequency domain identification problem would bring new ideas and lead to more interactions among the areas of system identification, learning theory and frequency analysis.