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.

Cite

Text

Wang et al. "FedSysID: A Federated Approach to Sample-Efficient System Identification." Proceedings of The 5th Annual Learning for Dynamics and Control Conference, 2023.

Markdown

[Wang et al. "FedSysID: A Federated Approach to Sample-Efficient System Identification." Proceedings of The 5th Annual Learning for Dynamics and Control Conference, 2023.](https://mlanthology.org/l4dc/2023/wang2023l4dc-fedsysid/)

BibTeX

@inproceedings{wang2023l4dc-fedsysid,
  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},
  year      = {2023},
  pages     = {1308-1320},
  volume    = {211},
  url       = {https://mlanthology.org/l4dc/2023/wang2023l4dc-fedsysid/}
}