Guaranteed non-asymptotic confidence regions in system identification

DOI10.1016/j.automatica.2005.05.005zbMath1090.93047OpenAlexW2100844674MaRDI QIDQ2573911

Erik Weyer, Marco C. Campi

Publication date: 25 November 2005

Published in: Automatica (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.automatica.2005.05.005

zbMATH Keywords

system identificationconfidence setsgeneral linear modelsfinite sample resultsuncertainty evaluation

Mathematics Subject Classification ID

Nonparametric tolerance and confidence regions (62G15) Identification in stochastic control theory (93E12)

Related Items (24)

Guaranteed characterization of exact non-asymptotic confidence regions as defined by LSCR and SPS ⋮ Least-squares estimation of a class of frequency functions: a finite sample variance expression ⋮ Identification of linear systems with multiplicative noise from multiple trajectory data ⋮ Asymptotic properties of SPS confidence regions ⋮ Non-asymptotic state-space identification of closed-loop stochastic linear systems using instrumental variables ⋮ Accuracy of linear multiple-input multiple-output (MIMO) models obtained by maximum likelihood estimation ⋮ Non-asymptotic model quality assessment of transfer functions at multiple frequency points ⋮ Optimal experimental design and some related control problems ⋮ System identification of complex and structured systems ⋮ A counterexample to the uniqueness of the asymptotic estimate in ARMAX model identification via the correlation approach ⋮ Parameter identification for nonlinear systems: guaranteed confidence regions through LSCR ⋮ Facing undermodelling in sign-perturbed-sums system identification ⋮ Covariance analysis in SISO linear systems identification ⋮ Iterative robust control: speeding up improvement through iterations ⋮ The nonasymptotic confidence set for parameters of a linear control object under an arbitrary external disturbance ⋮ On resampling and uncertainty estimation in linear system identification ⋮ Bayesian system identification via Markov chain Monte Carlo techniques ⋮ Discussion on: ``Why is resorting to fate wise? A critical look at randomized algorithms in systems and control ⋮ Non-asymptotic confidence regions for the parameters of EIV systems ⋮ Distribution-free uncertainty quantification for kernel methods by gradient perturbations ⋮ Non-asymptotic confidence regions for model parameters in the presence of unmodelled dynamics ⋮ Guaranteed non-asymptotic confidence regions in system identification ⋮ Bayesian frequentist bounds for machine learning and system identification ⋮ Perturbed datasets methods for hypothesis testing and structure of corresponding confidence sets

Cites Work

• Assessing the quality of identified models through the asymptotic theory -- when is the result reliable?
• Non-asymptotic quality assessment of generalised FIR models with periodic inputs
• On covariance function tests used in system identification
• Optimal estimation theory for dynamic systems with set membership uncertainty: An overview
• Completely separating groups in subsampling
• Model quality evaluation in set membership identification
• Non-asymptotic confidence ellipsoids for the least-squares estimate
• Bounded-error parameter estimation: Noise models and recursive algorithms
• The asymptotic model quality assessment for instrumental variable identification revisited
• Estimating linear time-invariant models of nonlinear time-varying systems
• Guaranteed non-asymptotic confidence regions in system identification
• H/sub ∞/ identification and model quality evaluation
• Membership set estimators: size, optimal inputs, complexity and relations with least squares
• Conditional central algorithms for worst case set-membership identification and filtering
• Sequential approximation of feasible parameter sets for identification with set membership uncertainty
• Identification of approximated hammerstein models in a worst-case setting
• Finite sample properties of system identification methods
• Using the bootstrap to estimate the variance in the case of undermodeling
• Exact Confidence Intervals in Regression Problems with Independent Symmetric Errors
• Bootstrap-based estimates of uncertainty in subspace identification methods

This page was built for publication: Guaranteed non-asymptotic confidence regions in system identification