FedSysID: A Federated Approach to Sample-Efficient System Identification

Han Wang, Leonardo Felipe Toso, James Anderson
Proceedings of The 5th Annual Learning for Dynamics and Control Conference, PMLR 211:1308-1320, 2023.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v211-wang23d, title = {FedSysID: A Federated Approach to Sample-Efficient System Identification}, author = {Wang, Han and Toso, Leonardo Felipe and Anderson, James}, booktitle = {Proceedings of The 5th Annual Learning for Dynamics and Control Conference}, pages = {1308--1320}, year = {2023}, editor = {Matni, Nikolai and Morari, Manfred and Pappas, George J.}, volume = {211}, series = {Proceedings of Machine Learning Research}, month = {15--16 Jun}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v211/wang23d/wang23d.pdf}, url = {https://proceedings.mlr.press/v211/wang23d.html}, 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.} }
Endnote
%0 Conference Paper %T FedSysID: A Federated Approach to Sample-Efficient System Identification %A Han Wang %A Leonardo Felipe Toso %A James Anderson %B Proceedings of The 5th Annual Learning for Dynamics and Control Conference %C Proceedings of Machine Learning Research %D 2023 %E Nikolai Matni %E Manfred Morari %E George J. Pappas %F pmlr-v211-wang23d %I PMLR %P 1308--1320 %U https://proceedings.mlr.press/v211/wang23d.html %V 211 %X 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.
APA
Wang, H., Toso, L.F. & Anderson, J.. (2023). FedSysID: A Federated Approach to Sample-Efficient System Identification. Proceedings of The 5th Annual Learning for Dynamics and Control Conference, in Proceedings of Machine Learning Research 211:1308-1320 Available from https://proceedings.mlr.press/v211/wang23d.html.

Related Material