Finite time identification in unstable linear systems
From MaRDI portal
Abstract: Identification of the parameters of stable linear dynamical systems is a well-studied problem in the literature, both in the low and high-dimensional settings. However, there are hardly any results for the unstable case, especially regarding finite time bounds. For this setting, classical results on least-squares estimation of the dynamics parameters are not applicable and therefore new concepts and technical approaches need to be developed to address the issue. Unstable linear systems arise in key real applications in control theory, econometrics, and finance. This study establishes finite time bounds for the identification error of the least-squares estimates for a fairly large class of heavy-tailed noise distributions, and transition matrices of such systems. The results relate the time length (samples) required for estimation to a function of the problem dimension and key characteristics of the true underlying transition matrix and the noise distribution. To establish them, appropriate concentration inequalities for random matrices and for sequences of martingale differences are leveraged.
Recommendations
Cites work
- Analysis of coexplosive processes
- AR Identification of Latent-Variable Graphical Models
- 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
- Convergence of adaptive control schemes using least-squares parameter estimates
- Dating the timeline of financial bubbles during the subprime crisis
- Discrete-time stochastic systems. Estimation and control.
- Generalization bounds for non-stationary mixing processes
- Generalization bounds for time series prediction with non-stationary processes
- scientific article; zbMATH DE number 3818787 (Why is no real title available?)
- scientific article; zbMATH DE number 3982362 (Why is no real title available?)
- scientific article; zbMATH DE number 44386 (Why is no real title available?)
- scientific article; zbMATH DE number 1095138 (Why is no real title available?)
- scientific article; zbMATH DE number 2199188 (Why is no real title available?)
- scientific article; zbMATH DE number 6193731 (Why is no real title available?)
- On Asymptotic Distributions of Estimates of Parameters of Stochastic Difference Equations
- Optimality of Fast-Matching Algorithms for Random Networks With Applications to Structural Controllability
- Regularized estimation and testing for high-dimensional multi-block vector-autoregressive models
- Regularized estimation in sparse high-dimensional time series models
- Small sample properties of forecasts from autoregressive models under structural breaks
- Sparse plus low rank network identification: a nonparametric approach
- Stochastic Systems
- Stochastic thresholds in event-triggered control: a consistent policy for quadratic control
- STRONG CONSISTENCY RESULTS FOR LEAST SQUARES ESTIMATORS IN GENERAL VECTOR AUTOREGRESSIONS WITH DETERMINISTIC TERMS
- Tests of Conditional Predictive Ability
- The red book of varieties and schemes. Includes the Michigan lectures (1974) on ``Curves and their Jacobians.
- Unified asymptotic theory for nearly unstable AR(\(p\)) processes
- User-friendly tail bounds for sums of random matrices
Cited in
(17)- System identifiability from finite time series
- Input perturbations for adaptive control and learning
- On adaptive linear-quadratic regulators
- Performance analysis of the compressed distributed least squares algorithm
- Identification Using Stability Restrictions
- Identification of Systems With Regime Switching and Unmodeled Dynamics
- Finite time LTI system identification
- scientific article; zbMATH DE number 7626780 (Why is no real title available?)
- scientific article; zbMATH DE number 7625185 (Why is no real title available?)
- Finite‐time sampled‐data H∞ control of Markovian jumping linear systems with mode‐dependent time‐varying delays
- Non-asymptotic state-space identification of closed-loop stochastic linear systems using instrumental variables
- Joint learning of linear time-invariant dynamical systems
- End-to-end guarantees for indirect data-driven control of bilinear systems with finite stochastic data
- Combining federated learning and control: a survey
- Joint learning of linear dynamical systems under smoothness constraints
- Learning linearized models from nonlinear systems under initialization constraints with finite data
- The nonstochastic control problem
This page was built for publication: Finite time identification in unstable linear systems
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1716481)
