Stochastic approximation algorithms for parallel and distributed processing

DOI10.1080/17442508708833475MaRDI QIDQ3785800zbMATH OpenOpenAlexFDO

Authors Harold J. Kushner, G. 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

asynchronous on- line optimizationcommunication networksMonte Carlo optimizationparallel processing methodsWeak convergence methods

Mathematics Subject Classification ID

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

Recommendations

• scientific article; zbMATH DE number 440437
• Distributed asynchronous deterministic and stochastic gradient optimization algorithms
• On W.P.1 Convergence of A Parallel Stochastic Approximation Algorithm
• Optimal quasi-convex combinations for stochastic approximation algorithms with parallel observers
• Parallel and bootstrapped stochastic approximation

Cites work

• An Invariant Measure Approach to the Convergence of Stochastic Approximations with State Dependent Noise
• Asymptotic Properties of Stochastic Approximations with Constant Coefficients
• scientific article; zbMATH DE number 3878095 (Why is no real title available?)
• scientific article; zbMATH DE number 3729228 (Why is no real title available?)
• scientific article; zbMATH DE number 3274494 (Why is no real title available?)
• Stability and Control of Stochastic Systems with Wide-band Noise Disturbances. I

Cited in

(38)

• On robustness of the Robbins-Monro method for parallel processing
• A stochastic quasigradient algorithm with variable metric
• A stopping rule for the Robbins-Monro method
• About Gaussian schemes in stochastic approximation
• Control of dynamic systems under the influence of singularly perturbed Markov chains
• Stability of Markov modulated discrete-time dynamic systems.
• Blind channel identification via stochastic approximation: constant step-size algorithms
• Closed-loop persistent identification of linear systems with unmodeled dynamics and stochastic disturbances
• Adaptive stochastic optimization using multiprocessors
• Wong-Zakai approximations for stochastic differential equations
• Joint robustness on noise and Lyapunov functions for parallel stochastic approximation algorithms
• Adaptive decentralized control under non-uniqueness of the optimal control
• A parallel version of a quasigradient methoid In stochastic control theory^∗
• scientific article; zbMATH DE number 440437 (Why is no real title available?)
• On W.P.1 Convergence of A Parallel Stochastic Approximation Algorithm
• On the stochastic and quasi-stochastic algorithms parallelization in modeling problems
• Asymptotic Properties of Distributed and Communicating Stochastic Approximation Algorithms
• A convergence property of Dubins' representation of distributions
• scientific article; zbMATH DE number 1190408 (Why is no real title available?)
• Stochastic fictitious play with continuous action sets
• scientific article; zbMATH DE number 1754723 (Why is no real title available?)
• Thompson sampling guided stochastic searching on the line for deceptive environments with applications to root-finding problems
• Parallel algorithms and probability of large deviation for stochastic convex optimization problems
• Parallel and bootstrapped stochastic approximation
• Optimal quasi-convex combinations for stochastic approximation algorithms with parallel observers
• Load Balancing in Hypercube Solution of Stochastic Optimization Problems
• Asynchronous stochastic approximation with differential inclusions
• Probabilistic bisection converges almost as quickly as stochastic approximation
• Stochastic Algorithms: Foundations and Applications
• Stochastic approximation algorithms: overview and recent trends.
• Asymptotically optimal controls of hybrid linear quadratic regulators in discrete time.
• Change-point monitoring for online stochastic approximations
• Charge-based control of DiffServ-like queues
• Some aspects of parallel and distributed iterative algorithms - a survey
• Asymptotic behavior of asynchronous stochastic approximation
• A stopping rule for stochastic approximation
• Identification of linear continuous-time systems under irregular and random output sampling
• Q-learning algorithms with random truncation bounds and applications to effective parallel computing

This page was built for publication: Stochastic approximation algorithms for parallel and distributed processing

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3785800)