Information-based complexity and nonparamteric worst-case system identification
The paper is a survey of nonparametric approaches to identification of linear dynamic systems under nonprobabilistic assumptions on uncertains. The authors, first, introduce definitions and basic results of the information-based complexity (IBC) theory, used in the paper. Nonparametric approaches developed in the last few years can be classified in two main categories, according to the norm in which the estimation errors are measured: \(H_ \infty\) and \(l_ 1\) methods. The \(H_ \infty\) setting assumes that the true system is linear time- invariant and the available information is represented by samples of frequence response of the system, corrupted by an \(l_ \infty\)-norm bound noise. The aim is to estimate a proper, stable finite-dimensional model. In the \(l_ 1\) setting, the aim is to identify the samples of the impulse of an unknown linear time-invariant system. They provide recent results on \(H_ \infty\), \(l_ 1\), and \(l_ \infty\) identification, with particular attention to (a) evaluation of the diameter of information, (b) convergence to zero of the diameter of information, and (c) computation of optimal and almost-optimal algorithms.
- scientific article; zbMATH DE number 926789
- Worst case system identification in H/sub ∞/: validation of a priori information, essentially optimal algorithms, and error bounds
- Linear and nonlinear algorithms for identification in H/sub infinity / with error bounds
- scientific article; zbMATH DE number 806815
- scientific article; zbMATH DE number 5773500
- L^ system approximation algorithms generated by summations
- Predictive self-tuning control by parameter bounding and worst-case design
- Complexity of identification of linear systems with rational transfer functions
- Model quality evaluation in set membership identification
- Squared and absolute errors in optimal approximation of nonlinear systems.
- Input-output identifiability of continuous-time linear systems
- Properties of least squares estimates in set membership identification
- Estimation of model quality
- Worst-case control-relevant identification
- Modelling of uncertain systems via linear programming
- Input design in worst-case system identification with quantized measurements
- \(H_{\infty}\) identification of ``soft uncertainty models
- Computation of local radius of information in SM-IBC identification of nonlinear systems
- Uncertainty, information and complexity in identification and control
- On the sample-complexity of \({\mathcal H}_\infty\) identification
- Persistent tracking and identification of regime-switching systems with structural uncertainties: unmodeled dynamics, observation bias, and nonlinear model mismatch
- System identification: regime switching, unmodeled dynamics, and binary sensors
- scientific article; zbMATH DE number 1332917 (Why is no real title available?)
- Almost sure convergence rates for system identification using binary, quantized, and regular sensors
- Optimality properties in finite sample li identification with bounded noise
- scientific article; zbMATH DE number 926781 (Why is no real title available?)
- Robust noise attenuation under stochastic noises and worst-case unmodelled dynamics
- Efficient numerical approximation of maximum entropy estimates
- Optimal and suboptimal algorithms in set membership identification
- On the information-based complexity of optimal reconstruction for nonlinear systems
- Robustness in \(H_\infty\) identification
- Optimal conditional estimation: Average case setting
- Nonlinear system identification in Sobolev spaces
- LTI modelling of NFIR systems: near-linearity and control, LS estimation and linearization
- On robustness in control and LTI identification: near-linearity and non-conic uncertainty
This page was built for publication: Information-based complexity and nonparamteric worst-case system identification
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1330145)
