New stochastic approximation algorithms with adaptive step sizes

DOI10.1007/s11590-011-0380-5zbMath1261.90057OpenAlexW1991701290MaRDI QIDQ1926628

Zi Xu, Yu-Hong Dai

Publication date: 28 December 2012

Published in: Optimization Letters (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s11590-011-0380-5

zbMATH Keywords

stochastic approximationRobbins-Monro algorithmadaptive step sizeKesten algorithm

Mathematics Subject Classification ID

Nonlinear programming (90C30) Stochastic programming (90C15)

Related Items

A gradient method for unconstrained optimization in noisy environment ⋮ Descent direction method with line search for unconstrained optimization in noisy environment ⋮ Adaptive stochastic approximation algorithm ⋮ A new hybrid stochastic approximation algorithm ⋮ A nonmonotone line search method for noisy minimization ⋮ Some convergence theorems for RM algorithm

Uses Software

• minpack

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Approximation of the distribution of convergence times for stochastic global optimisation
• A combined direction stochastic approximation algorithm
• Adaptive estimation algorithms (convergence, optimality, stability)
• Nonconvex stochastic optimization for model reduction
• Accelerated Stochastic Approximation
• Testing Unconstrained Optimization Software
• Accelerated Stochastic Approximation
• Introduction to Stochastic Search and Optimization
• Gradient Convergence in Gradient methods with Errors
• An Extension of the Robbins-Monro Procedure
• On Asymptotic Normality in Stochastic Approximation
• A Stochastic Approximation Method
• Stochastic optimization: Algorithms and applications. Conference, Univ. of Florida, Tallahassee, FL, USA, February 20--22, 2000