Remarks on the martingale hyperconvergence theorem and the convergence analysis of the forgetting factor least squares algorithms (Q2744506)
From MaRDI portal
 | This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use this page instead for the normal view: Remarks on the martingale hyperconvergence theorem and the convergence analysis of the forgetting factor least squares algorithms |
scientific article; zbMATH DE number 1649080
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | Remarks on the martingale hyperconvergence theorem and the convergence analysis of the forgetting factor least squares algorithms |
scientific article; zbMATH DE number 1649080 |
Statements
4 March 2004
0 references
martingale hyperconvergence theorem
0 references
upper bounded
0 references
parameter estimation error
0 references
forgetting factor least squares algorithms
0 references
linear regression time-varying stochastic system
0 references
Remarks on the martingale hyperconvergence theorem and the convergence analysis of the forgetting factor least squares algorithms (English)
0 references
The authors give an alternative proof for the martingale hyperconvergence theorem (MHCT) [cf. \textit{F. Ding}, Control Theory Appl. 14, No. 1, 90-95 (Chinese) (1997)]. Moreover, by using this theorem, the upper boundedness of the parameter estimation error of forgetting factor least squares algorithms for the linear regression time-varying stochastic system \((y(t)=\Phi^T(t)\theta(t-1)+v(t))\) is obtained. Compared with the former results given in the above-mentioned paper, the identification precision and the boundedness of the covariance matrix of the proposed problem are well improved.
0 references
