Centralized and Distributed Online Learning for Sparse Time-Varying Optimization

The development of online algorithms to track time-varying systems has drawn a lot attention in the last years, particular framework convex optimization. Meanwhile, sparse optimization emerged as powerful tool deal with widespread applications, ranging from dynamic compressed sensing parsimonious system identification. In most literature on problems, some prior information system's evolution is assumed be available. contrast, this article, we propose an learning approach, which does not employ given model and suitable for adversarial frameworks. Specifically, develop centralized distributed algorithms, theoretically analyze them terms regret, perspective. Furthermore, numerical experiments that illustrate their practical effectiveness.