On the worst-case divergence of the least-squares algorithm

DOI10.1016/S0167-6911(97)00093-5MaRDI QIDQ1128512zbMATH OpenOpenAlexFDO

Authors Hüseyin Akçay, Brett Ninness

Publication date 13 August 1998

Published in Systems \& Control Letters (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/s0167-6911(97)00093-5

zbMATH Keywords

least-squaresdivergenceFIR model structuresidentification in \({\mathcal H}_{\infty}\)time-domain data

Mathematics Subject Classification ID

System identification (93B30) Least squares and related methods for stochastic control systems (93E24)

Recommendations

• Worst-case errors of linear algorithms for identification in H
• Worst-case analysis of the least-squares method and related identification methods
• Properties of least squares estimates in set membership identification
• Analysis of linear methods for robust identification in \(\ell_ 1\)

Cites work

• scientific article; zbMATH DE number 3997615 (Why is no real title available?)
• scientific article; zbMATH DE number 3010958 (Why is no real title available?)
• Analysis of linear methods for robust identification in \(\ell_ 1\)
• Asymptotic properties of black-box identification of transfer functions
• Asymptotic variance expressions for identified black-box transfer function models
• Control oriented system identification: a worst-case/deterministic approach in H/sub infinity /
• Least squares type algorithms for identification in the presence of modeling uncertainty
• Membership set estimators: size, optimal inputs, complexity and relations with least squares
• On covariance function tests used in system identification
• On the time complexity of worst-case system identification
• Optimality properties in finite sample l_i identification with bounded noise
• Properties of least squares estimates in set membership identification
• Robust identification and Galois sequences
• The least squares algorithm, parametric system identification and bounded noise
• The least-squares identification of FIR systems subject to worst-case noise
• The modeling of uncertainty in control systems. Proceedings of the 1992 Santa Barbara Workshop held at the University of California, Santa Barbara, CA, USA, June 18-20, 1992
• The sample complexity of worst-case identification of FIR linear systems
• Worst case system identification in \(\ell{}_ 1\): Optimal algorithms and error bounds
• Worst-case analysis of the least-squares method and related identification methods
• Worst-case control-relevant identification
• Worst-case identification in \(\ell_ 2\): Linear and nonlinear algorithms

Cited in

(6)

• Optimal worst case estimation for LPV--FIR models with bounded errors
• \(H_{\infty}\) set membership identification: a survey
• Unified set membership theory for identification, prediction and filtering of nonlinear systems
• A generalization of a standard inequality for Hardy space \(H_1\)
• Properties of least squares estimates in set membership identification
• Worst-case recovery guarantees for least squares approximation using random samples

This page was built for publication: On the worst-case divergence of the least-squares algorithm

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1128512)