FedSysID: A Federated Approach to Sample-Efficient System Identification
This work addresses the question of how multiple clients collaboratively learn dynamical models in the presence of heterogeneity by posing the problem as a federated learning problem and characterize the tension between achievable performance and system heterogeneity.
Han Wang, L. F. Toso, James Anderson
· Conference on Learning for D... · 28 citations
· ⚡2