FedSysID: A Federated Approach to Sample-Efficient System Identification

arXiv:2211.14393v2 Announce Type: replace 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.

Source: arXiv cs.LG | 2026-09-29