FedSysID: A Federated Approach to Sample-Efficient System Identification

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.

Paper accepted at L4DC 2023. This version refines the error bounds and correct typos in the paper

Machine Learning (cs.LG); Systems and Control (eess.SY); Optimization and Control (math.OC)

arXiv:2211.14393 [cs.LG]

(or arXiv:2211.14393v2 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2211.14393 Focus to learn more arXiv-issued DOI via DataCite

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.