A stopping rule for the Robbins-Monro method

DOI10.1007/BF00939741zbMath0687.62068OpenAlexW2053571628MaRDI QIDQ1263202

G. George Yin

Publication date: 1990

Published in: Journal of Optimization Theory and Applications (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/bf00939741

zbMATH Keywords

weak convergenceasymptotic normalitystopping rulemoving averagelimit behaviorcorrelated noise processessequentially determined confidence ellipsoidsstationary phi-mixingstopped Robbins-Monro process

Mathematics Subject Classification ID

Central limit and other weak theorems (60F05) Stochastic approximation (62L20) Optimal stopping in statistics (62L15)

Related Items (9)

Some results about averaging in stochastic approximation ⋮ Identification error bounds and asymptotic distributions for systems with structural uncertainties ⋮ The Stochastic Auxiliary Problem Principle in Banach Spaces: Measurability and Convergence ⋮ A stopping rule for stochastic approximation ⋮ On H-valued Robbins-Monro processes ⋮ A Resampling-Based Stochastic Approximation Method for Analysis of Large Geostatistical Data ⋮ Recursive algorithms for trailing stop: Stochastic approximation approach ⋮ How does a stochastic optimization/approximation algorithm adapt to a randomly evolving optimum/root with jump Markov sample paths ⋮ Stopping criteria for, and strong convergence of, stochastic gradient descent on Bottou-Curtis-Nocedal functions

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• A stopped stochastic approximation algorithm
• Stochastic approximation methods for constrained and unconstrained systems
• On W.P.1 Convergence of A Parallel Stochastic Approximation Algorithm
• Stochastic approximation algorithms for parallel and distributed processing
• On a new stopping rule for stochastic approximation
• Stochastic Approximation and Large Deviations: Upper Bounds and <scp>w.p.1</scp> Convergence
• Local Convergence of Martingales and the Law of Large Numbers
• Characterization Theorems for Certain Stochastic Processes
• Stochastic Estimation of the Maximum of a Regression Function
• A Stochastic Approximation Method

This page was built for publication: A stopping rule for the Robbins-Monro method