On a new stopping rule for stochastic approximation
From MaRDI portal
Publication:3962370
DOI10.1007/BF00535715zbMath0497.62076MaRDI QIDQ3962370
Henry I. Braun, Donna F. Stroup
Publication date: 1982
Published in: Zeitschrift für Wahrscheinlichkeitstheorie und verwandte Gebiete (Search for Journal in Brave)
asymptotic normality; Wiener process; small sample properties; Robbins-Monro process; new stopping rule; first passage time of F-statistic criterion
62L20: Stochastic approximation
60G40: Stopping times; optimal stopping problems; gambling theory
62L12: Sequential estimation
Related Items
Design issues for generalized linear models: a review, Non-asymptotic confidence bounds for stochastic approximation algorithms with constant step size, A stopping rule for stochastic approximation, A stopped stochastic approximation algorithm, Fixed-width interval estimation of the minimum point of a regression function based on the Kiefer-Wolfowitz procedure, A stopping rule for the Robbins-Monro method, Some results about averaging in stochastic approximation, Stochastic approximation models in estimating productivity, Wear convergence of stochastic approximation processes with random indices
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Adaptive design and stochastic approximation
- On a Class of Stochastic Approximation Processes
- Consistency and asymptotic efficiency of slope estimates in stochastic approximation schemes
- An invariance principle for the Robbins-Monro process in a Hilbert space
- Functional and random central limit theorems for the Robbins-Munro process
- Bounded Length Confidence Intervals for the Zero of a Regression Function
- On the Asymptotic Theory of Fixed-Width Sequential Confidence Intervals for the Mean
- Asymptotic Distribution of Stochastic Approximation Procedures
- Stopping times for stochastic approximation procedures
- A Stochastic Approximation Method
- Approximation Methods which Converge with Probability one
- On a Stochastic Approximation Method