Asynchronous Stochastic Approximations
- 1 May 1998
- journal article
- Published by Society for Industrial & Applied Mathematics (SIAM) in SIAM Journal on Control and Optimization
- Vol. 36 (3) , 840-851
- https://doi.org/10.1137/s0363012995282784
Abstract
The asymptotic behavior of a distributed, asynchronous stochastic approximation scheme is analyzed in terms of a limiting nonautonomous differential equation. The relation between the latter and the relative values of suitably rescaled relative frequencies of updates of different components is underscored.Keywords
This publication has 10 references indexed in Scilit:
- An analog scheme for fixed point computation. I. TheoryIEEE Transactions on Circuits and Systems I: Regular Papers, 1997
- Distributed computation of fixed points of ∞-nonexpansive mapsProceedings - Mathematical Sciences, 1996
- Managing interprocessor delays in distributed recursive algorithmsSādhanā, 1994
- On the Convergence of Stochastic Iterative Dynamic Programming AlgorithmsNeural Computation, 1994
- Recursive Stochastic Algorithms for Global Optimization in $\mathbb{R}^d $SIAM Journal on Control and Optimization, 1991
- Stochastic evolutionary game dynamics∗Theoretical Population Biology, 1990
- Convergent activation dynamics in continuous time networksNeural Networks, 1989
- Stochastic approximation algorithms for parallel and distributed processingStochastics, 1987
- Asymptotic Properties of Distributed and Communicating Stochastic Approximation AlgorithmsSIAM Journal on Control and Optimization, 1987
- Distributed asynchronous deterministic and stochastic gradient optimization algorithmsIEEE Transactions on Automatic Control, 1986