Tools
Tools
Charamza, P. (1989). Non-Standard Stochastic Approximation Scheme. IIASA Working Paper. IIASA, Laxenburg, Austria: WP-89-023
Preview |
Text
WP-89-023.pdf Download (649kB) | Preview |
Abstract
An adaptive stochastic approximation scheme is suggested for solving a system of equations defined by functions whose values are available only through random observations on a given lattice. To improve the performance of the basic stochastic approximation scheme in the presence of outliers, the author uses isotonic and quasi-isotonic regression to fit the observed function values. The convergence of the algorithm is proved.
| Item Type: | Monograph (IIASA Working Paper) |
|---|---|
| Research Programs: | Adaption and Optimization (ADO) Young Scientists Summer Program (YSSP) |
| Depositing User: | IIASA Import |
| Date Deposited: | 15 Jan 2016 02:00 |
| Last Modified: | 27 Aug 2021 17:13 |
| URI: | https://pure.iiasa.ac.at/3321 |
Actions (login required)
 |
View Item |