Stochastic approximation method with gradient averaging for unconstrained problems

DOI10.1109/TAC.1983.1103184MaRDI QIDQ3316422zbMATH OpenFDO

Authors Andrzej Ruszczyński, Wojciech Syski

Publication date 1983

Published in IEEE Transactions on Automatic Control (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1109/TAC.1983.1103184

zbMATH Keywords

convergence theoremsstochastic gradient methodtwo-step multidimensional stochastic approximation procedureunconstrained optimization

Mathematics Subject Classification ID

Stochastic approximation (62L20) Methods of reduced gradient type (90C52)

Recommendations

• scientific article; zbMATH DE number 3963027
• scientific article; zbMATH DE number 3994824
• New method of stochastic approximation type
• Stochastic Approximation with Averaging of the Iterates: Optimal Asymptotic Rate of Convergence for General Processes
• Weighted Means in Stochastic Approximation of Minima

Cited in

(21)

• On convergence of the stochastic subgradient method with on-line stepsize rules
• A method of stochastic subgradients with complete feedback stepsize rule for convex stochastic approximation problems
• New method of stochastic approximation type
• Infinitesimal perturbation analysis for second derivative estimation and design of manufacturing flow controllers
• Optimization via simulation: A review
• Stochastic proximal gradient methods for nonconvex problems in Hilbert spaces
• Stochastic intermediate gradient method for convex optimization problems
• scientific article; zbMATH DE number 3922382 (Why is no real title available?)
• Stochastic iteration for a constrained optimization problem
• On h–valued stochastic approximation: finite dimenstional projections
• Ergodic convergence in subgradient optimization
• On stochastic gradient and subgradient methods with adaptive steplength sequences
• A two Timescale Stochastic Approximation Scheme for Simulation-Based Parametric Optimization
• Risk-averse learning by temporal difference methods with Markov risk measures
• A Single Timescale Stochastic Approximation Method for Nested Stochastic Optimization
• A merit function approach to the subgradient method with averaging
• Stochastic approximation algorithms: overview and recent trends.
• Hessian averaging in stochastic Newton methods achieves superlinear convergence
• Zeroth-order Riemannian averaging stochastic approximation algorithms
• A Kalman-tracking filter approach to nonlinear programming
• A stochastic conjugate gradient method for the approximation of functions

This page was built for publication: Stochastic approximation method with gradient averaging for unconstrained problems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3316422)