FedSysID: A Federated Approach to Sample-Efficient System Identification

Author name not available (Why is that?)

Publication date: 25 November 2022

Abstract: We study the problem of learning a linear system model from the observations of

M

clients. The catch: Each client is observing data from a different dynamical system. This work addresses the question of how multiple clients collaboratively learn dynamical models in the presence of heterogeneity. We pose this problem as a federated learning problem and characterize the tension between achievable performance and system heterogeneity. Furthermore, our federated sample complexity result provides a constant factor improvement over the single agent setting. Finally, we describe a meta federated learning algorithm, FedSysID, that leverages existing federated algorithms at the client level.

Has companion code repository: https://github.com/jd-anderson/federated-id

This page was built for publication: FedSysID: A Federated Approach to Sample-Efficient System Identification

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6418513)