Stochastic approximation algorithms for parallel and distributed processing

DOI10.1080/17442508708833475zbMath0643.62055OpenAlexW1963747782MaRDI QIDQ3785800

Harold J. Kushner, G. George Yin

Publication date: 1987

Published in: Stochastics (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1080/17442508708833475

zbMATH Keywords

communication networksMonte Carlo optimizationparallel processing methodsasynchronous on- line optimizationWeak convergence methods

Mathematics Subject Classification ID

Central limit and other weak theorems (60F05) Stochastic approximation (62L20) Parallel numerical computation (65Y05) Theory of computing (68Q99)

Related Items

Closed-loop persistent identification of linear systems with unmodeled dynamics and stochastic disturbances, Asynchronous stochastic approximation with differential inclusions, Wong-Zakai approximations for stochastic differential equations, Control of dynamic systems under the influence of singularly perturbed Markov chains, On robustness of the Robbins-Monro method for parallel processing, Change-point monitoring for online stochastic approximations, Stochastic fictitious play with continuous action sets, A stopping rule for stochastic approximation, Identification of linear continuous-time systems under irregular and random output sampling, Stability of Markov modulated discrete-time dynamic systems., Q-learning algorithms with random truncation bounds and applications to effective parallel computing, A stochastic quasigradient algorithm with variable metric, Charge-based control of DiffServ-like queues, Stochastic approximation algorithms: overview and recent trends., Asymptotically optimal controls of hybrid linear quadratic regulators in discrete time., A stopping rule for the Robbins-Monro method, Probabilistic Bisection Converges Almost as Quickly as Stochastic Approximation, Adaptive decentralized control under non-uniqueness of the optimal control, On W.P.1 Convergence of A Parallel Stochastic Approximation Algorithm, Unnamed Item, Some aspects of parallel and distributed iterative algorithms - a survey, About Gaussian schemes in stochastic approximation, Blind channel identification via stochastic approximation: constant step-size algorithms

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• An Invariant Measure Approach to the Convergence of Stochastic Approximations with State Dependent Noise
• Asymptotic Properties of Stochastic Approximations with Constant Coefficients
• Stability and Control of Stochastic Systems with Wide-band Noise Disturbances. I