Joint learning of linear time-invariant dynamical systems

DOI10.1016/J.AUTOMATICA.2024.111635MaRDI QIDQ6550232zbMATH OpenFDO

Authors Aditya Modi, Mohamad Kazem Shirani Faradonbeh, Ambuj Tewari, George Michailidis

Publication date 5 June 2024

Published in Automatica (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/J.AUTOMATICA.2024.111635

zbMATH Keywords

autoregressive processesdata sharingfinite time identificationjoint estimationmultiple linear systems

Mathematics Subject Classification ID

System identification (93B30) Linear systems in control theory (93C05)

Review text

The problem of jointly learning multiple linear time-invariant dynamical systems is considered under the assumption that the transition unknown matrices can be expressed using an unknown shared basis matrices. The main result here are the finite-time estimation error bounds. Influence of dimension, spectral radius, eigenvalues multiplicity, tail properties of the noise processes, and heterogeneity among the systems on the estimation accuracy is studied. The illustrative example is included to compare the estimation errors of proposed approach with the conventional least-squares estimates of the transition matrices for each system individually.

Recommendations

• Gradient descent learns linear dynamical systems
• Identification of linear dynamical systems and machine learning
• Learning dynamical systems in a stationary environment
• Finite time LTI system identification
• Parameter estimation on linear time-varying systems

Cites work

• A new look at the statistical model identification
• A nonlinear programming algorithm for solving semidefinite programs via low-rank factorization
• Asymptotic properties of general autoregressive models and strong consistency of least-squares estimates of their parameters
• Asymptotic theory of least squares estimators for nearly unstable processes under strong dependence
• Bounds for linear multi-task learning
• Convergence properties of adaptive systems and the definition of exponential stability
• Estimating the dimension of a model
• Factor Models With Real Data: A Robust Estimation of the Number of Factors
• Finite time identification in unstable linear systems
• Finite-Time Adaptive Stabilization of Linear Systems
• High-dimensional probability. An introduction with applications in data science
• scientific article; zbMATH DE number 5957307 (Why is no real title available?)
• scientific article; zbMATH DE number 1179314 (Why is no real title available?)
• Input perturbations for adaptive control and learning
• Network Granger causality with inherent grouping structure
• Non-convex optimization for machine learning
• On adaptive linear-quadratic regulators
• Persistence of excitation in linear systems
• Regularized joint estimation of related vector autoregressive models
• The benefit of multitask representation learning
• Time series and panel data econometrics

Cited in

(2)

• Combining federated learning and control: a survey
• Joint learning of linear dynamical systems under smoothness constraints

This page was built for publication: Joint learning of linear time-invariant dynamical systems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6550232)