A stopped stochastic approximation algorithm (Q1107246)
From MaRDI portal
!
This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:
scientific article; zbMATH DE number 4064312
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | A stopped stochastic approximation algorithm |
scientific article; zbMATH DE number 4064312 |
Statements
A stopped stochastic approximation algorithm (English)
0 references
1988
0 references
A stopping time problem for a multidimensional Robbins-Monro stochastic approximation procedure is studied. The stopping rule is determined such that the procedure will be terminated if the unknown parameter \(\theta\) (the root of the regression function) is inside a desired ellipsoidal confidence region with high probability. Some usual assumptions are supposed to be valid for this stochastic approximation procedure. The noise processes are supposed to fulfill a condition of martingale type but not to be necessarily independent. The stopped process is then shown to be asymptotically normal by means of weak convergence methods. The construction of the desired confidence ellipsoids is described.
0 references
multidimensional Robbins-Monro stochastic approximation procedure
0 references
root of the regression function
0 references
ellipsoidal confidence region
0 references
weak convergence
0 references
0 references
0.9154289960861206
0 references
