Accelerated convergence effect in stochastic programming algorithms with correlated noise (Q1083367): Difference between revisions
From MaRDI portal
Created a new Item |
Set profile property. |
||
| (One intermediate revision by one other user not shown) | |||
| Property / MaRDI profile type | |||
| Property / MaRDI profile type: MaRDI publication profile / rank | |||
Normal rank | |||
| links / mardi / name | links / mardi / name | ||
Latest revision as of 03:08, 5 March 2024
scientific article
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | Accelerated convergence effect in stochastic programming algorithms with correlated noise |
scientific article |
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
