A stopping rule for stochastic approximation

DOI10.1016/J.AUTOMATICA.2015.06.029MaRDI QIDQ900181zbMATH OpenOpenAlexFDO

Authors Takayuki Wada, Yasumasa Fujisaki

Publication date 21 December 2015

Published in Automatica (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.automatica.2015.06.029

zbMATH Keywords

adaptive controlrandomized algorithmsstochastic approximationsystem identification

Mathematics Subject Classification ID

System identification (93B30) Adaptive control/observation systems (93C40)

Recommendations

• Stopping rules for optimization algorithms based on stochastic approximation
• A stopped stochastic approximation algorithm
• A stopping rule for the Robbins-Monro method
• Stochastic approximation: Theory and applications
• scientific article; zbMATH DE number 4108650

Cites work

• A Stochastic Approximation Method
• A stopped stochastic approximation algorithm
• A stopping rule for the Robbins-Monro method
• Convergence and convergence rate of iterative stochastic algorithms. I: General case
• Distributed Subgradient Methods for Multi-Agent Optimization
• scientific article; zbMATH DE number 5348356 (Why is no real title available?)
• scientific article; zbMATH DE number 48727 (Why is no real title available?)
• Introduction to Stochastic Search and Optimization
• Multivariate stochastic approximation using a simultaneous perturbation gradient approximation
• New Approach to Recursive Identification for ARMAX Systems
• Non-asymptotic confidence bounds for stochastic approximation algorithms with constant step size
• On a Class of Stochastic Approximation Processes
• On a new stopping rule for stochastic approximation
• On Asymptotic Normality in Stochastic Approximation
• On stochastic gradient and subgradient methods with adaptive steplength sequences
• Output Tracking for Nonlinear Stochastic Systems by Iterative Learning Control
• Randomized algorithms for analysis and control of uncertain systems. With applications
• Recursive identification of errors-in-variables Wiener systems
• Stochastic approximation algorithms for parallel and distributed processing
• Stochastic approximation and its applications
• Stochastic consensus over noisy networks with Markovian and arbitrary switches
• Stochastic Consensus Seeking With Noisy and Directed Inter-Agent Communication: Fixed and Randomly Varying Topologies
• Stochastic Estimation of the Maximum of a Regression Function
• Stopping times for stochastic approximation procedures
• The asymptotic validity of sequential stopping rules for stochastic simulations

Cited in

(16)

• Stopping rules and the likelihood function
• Probabilistic characteristics of one stopping rule for steady control
• Stopping rules for a class of sampling-based stochastic programming algorithms
• Finite-sample performance of absolute precision stopping rules
• Stopping rules for optimization algorithms based on stochastic approximation
• Time averaging algorithms with stopping rules for multi-agent consensus with noisy measurements
• A Lepskij-type Stopping-Rule for Newton-type Methods with Random Noise
• scientific article; zbMATH DE number 3864400 (Why is no real title available?)
• scientific article; zbMATH DE number 3874334 (Why is no real title available?)
• scientific article; zbMATH DE number 5558051 (Why is no real title available?)
• scientific article; zbMATH DE number 4108650 (Why is no real title available?)
• Miscellanea. A stopping rule for the continual reassessment method
• A consensus protocol over noisy two-layered networks with cooperative and antagonistic interactions
• A stopping rule for least-squares identification
• The stochastic auxiliary problem principle in Banach spaces: measurability and convergence
• Multi-agent consensus with stopping rules under bounded measurement noise

This page was built for publication: A stopping rule for stochastic approximation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q900181)