A stopped stochastic approximation algorithm

DOI10.1016/0167-6911(88)90083-7MaRDI QIDQ1107246zbMATH OpenOpenAlexFDO

Authors G. Yin

Publication date 1988

Published in Systems \& Control Letters (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/0167-6911(88)90083-7

zbMATH Keywords

ellipsoidal confidence regionmultidimensional Robbins-Monro stochastic approximation procedureroot of the regression functionweak convergence

Mathematics Subject Classification ID

Central limit and other weak theorems (60F05) Stopping times; optimal stopping problems; gambling theory (60G40) Optimal stopping in statistics (62L15) Stochastic approximation (62L20)

Review text

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.

Recommendations

• A stopping rule for the Robbins-Monro method
• scientific article; zbMATH DE number 4108650
• scientific article; zbMATH DE number 4085419
• scientific article; zbMATH DE number 3874334
• Non-asymptotic confidence bounds for stochastic approximation algorithms with constant step size

Cites work

• A Stochastic Approximation Method
• Asymptotic properties of least-squares estimates in stochastic regression models
• Consistency and asymptotic efficiency of slope estimates in stochastic approximation schemes
• Estimation Following a Sequentially Designed Experiment
• scientific article; zbMATH DE number 3878095 (Why is no real title available?)
• scientific article; zbMATH DE number 3951715 (Why is no real title available?)
• scientific article; zbMATH DE number 3960871 (Why is no real title available?)
• scientific article; zbMATH DE number 3658755 (Why is no real title available?)
• scientific article; zbMATH DE number 3553601 (Why is no real title available?)
• scientific article; zbMATH DE number 3274494 (Why is no real title available?)
• scientific article; zbMATH DE number 3103824 (Why is no real title available?)
• Local Convergence of Martingales and the Law of Large Numbers
• On a new stopping rule for stochastic approximation
• Stopping times for stochastic approximation procedures

Cited in

(8)

• A stopping rule for the Robbins-Monro method
• Some results about averaging in stochastic approximation
• Asymptotic confidence regions of stochastic approximation procedures in Hilbert spaces
• scientific article; zbMATH DE number 3874334 (Why is no real title available?)
• scientific article; zbMATH DE number 4085419 (Why is no real title available?)
• scientific article; zbMATH DE number 4108650 (Why is no real title available?)
• Non-asymptotic confidence bounds for stochastic approximation algorithms with constant step size
• A stopping rule for stochastic approximation

This page was built for publication: A stopped stochastic approximation algorithm

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1107246)