FedSysID: A Federated Approach to Sample-Efficient System Identification
This work addresses collaborative system identification in heterogeneous settings, offering incremental gains for distributed learning applications.
The paper tackles the problem of learning linear system models from multiple clients observing different dynamical systems, proposing a federated learning approach that achieves a constant factor improvement in sample complexity over single-agent methods.
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.