mlsanityData to 14 Oct 2026

FedSysID: A Federated Approach to Sample-Efficient System Identification

arXiv 2211.14393 ↗First posted 25 Nov 2022cs.LG cs.SY eess.SYcited by 17

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 17 papers in the map (data through 14 Oct 2026). Builds on 22 of its 31 references that are in the map. First posted on arXiv 25 Nov 2022.

Builds on

22 of 31 references.

References · 22

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2019Advances and Open Problems in Federated Learningcited by 3,046
  3. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,475
  4. 2016Federated Optimization: Distributed Machine Learning for On-Device Intelligencecited by 564
  5. 2018A Hybrid Approach to Privacy-Preserving Federated Learningcited by 210
  6. 2017On the Sample Complexity of the Linear Quadratic Regulatorcited by 159
  7. 2018Learning Without Mixing: Towards A Sharp Analysis of Linear System Identificationcited by 158
  8. 2020Minibatch vs Local SGD for Heterogeneous Distributed Learningcited by 147
  9. 2021Linear Convergence in Federated Learning: Tackling Client Heterogeneity and Sparse Gradientscited by 123
  10. 2020FedSplit: An algorithmic framework for fast federated optimizationcited by 108
  11. 2018Near optimal finite time identification of arbitrary linear dynamical systemscited by 89
  12. 2018Non-asymptotic Identification of LTI Systems from a Single Trajectorycited by 78
10 more
  1. 2019Learning Linear Dynamical Systems with Semi-Parametric Least Squarescited by 58
  2. 2022Statistical Learning Theory for Control: A Finite Sample Perspectivecited by 53
  3. 2020Non-asymptotic Identification of Linear Dynamical Systems Using Multiple Trajectoriescited by 38
  4. 2022FedADMM: A Federated Primal-Dual Algorithm Allowing Partial Participationcited by 36
  5. 2021FedDR -- Randomized Douglas-Rachford Splitting Algorithms for Nonconvex Federated Composite Optimizationcited by 29
  6. 2020Finite-time Identification of Stable Linear Systems: Optimality of the Least-Squares Estimatorcited by 26
  7. 2019Learning Sparse Dynamical Systems from a Single Sample Trajectorycited by 20
  8. 2021Linear Systems can be Hard to Learncited by 20
  9. 2022Identifying the Dynamics of a System by Leveraging Data from Similar Systemscited by 15
  10. 2021Large-Scale System Identification Using a Randomized SVDcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 4; 2024: 6; 2025: 5; 2026: 2.

17 papers.

Sort:

By area:

  1. 2024Finite-Time Analysis of On-Policy Heterogeneous Federated Reinforcement Learningcited by 31
  2. 2023Improved Communication Efficiency in Federated Natural Policy Gradient via ADMM-based Gradient Updatescited by 21
  3. 2024Meta-Learning Linear Quadratic Regulators: A Policy Gradient MAML Approach for Model-free LQRcited by 17
  4. 2023Sample-Efficient Linear Representation Learning from Non-IID Non-Isotropic Datacited by 13
  5. 2023Learning Personalized Models with Clustered System Identificationcited by 11
  6. 2023Robot Fleet Learning via Policy Mergingcited by 11
  7. 2024Asynchronous Heterogeneous Linear Quadratic Regulator Designcited by 4
  8. 2024A survey on secure decentralized optimization and learningcited by 4
  9. 2024Combining Federated Learning and Control: A Surveycited by 3
  10. 2025Redefining Clustered Federated Learning for System Identification: The Path of ClusterCraftcited by 2
  11. 2025Federated Nonlinear System Identificationcited by 1
  12. 2025Adversarially Robust Multitask Adaptive Controlcited by 1
5 more
  1. 2025Harnessing Data from Clustered LQR Systems: Personalized and Collaborative Policy Optimizationcited by 1
  2. 2024Joint Learning of Linear Dynamical Systems under Smoothness Constraintscited by 0
  3. 2025A State Alignment-Centric Approach to Federated System Identification: The FedAlign Frameworkcited by 0
  4. 2026Eigenspace-Based Clustering for Personalized System Identificationcited by 0
  5. 2026Large Stepsizes Federated Learning on Logistic Regression with Linearly Separable Data: The Case of Heterogeneous Devicescited by 0