Accelerated convergence effect in stochastic programming algorithms with correlated noise (Q1083367)
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: Accelerated convergence effect in stochastic programming algorithms with correlated noise |
scientific article; zbMATH DE number 3976784
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | Accelerated convergence effect in stochastic programming algorithms with correlated noise |
scientific article; zbMATH DE number 3976784 |
Statements
Accelerated convergence effect in stochastic programming algorithms with correlated noise (English)
0 references
1986
0 references
A sum-difference inequality is obtained, whereby the convergence rate can be estimated in the Robbins-Monro mean-square algorithm with correlated additive noise. It is shown that, when the noise correlation functions has certain properties, there is an increase in the rate of asymptotic convergence to zero of the mean norm-squared of the error.
0 references
sum-difference inequality
0 references
Robbins-Monro mean-square algorithm
0 references
correlated additive noise
0 references
asymptotic convergence
0 references
