ASYMPTOTIC AGREEMENT AND CONVERGENCE OF ASYNCHRONOUS STOCHASTIC ALGORITHMS.

Shu Li, Tamer Basar

Research output: Contribution to journalConference article

Abstract

Results on the convergence and asymptotic agreement of a class of asynchronous distributed algorithms which are in general time-varying, memory-dependent, and not necessarily associated with the optimization of a common cost functional are presented. It is shown that convergence and agreement can be reached by distributed learning and computation under a number of conditions, in which case a separation of fast and slow parts of the algorithm is possible, leading to a separation of the estimation part from the main algorithm.

Original languageEnglish (US)
Pages (from-to)242-247
Number of pages6
JournalProceedings of the IEEE Conference on Decision and Control
StatePublished - Dec 1 1986

Fingerprint

Asynchronous Algorithms
Stochastic Algorithms
Distributed Algorithms
Parallel algorithms
Time-varying
Data storage equipment
Optimization
Dependent
Costs
Class
Learning

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Modeling and Simulation
  • Control and Optimization

Cite this

ASYMPTOTIC AGREEMENT AND CONVERGENCE OF ASYNCHRONOUS STOCHASTIC ALGORITHMS. / Li, Shu; Basar, Tamer.

In: Proceedings of the IEEE Conference on Decision and Control, 01.12.1986, p. 242-247.

Research output: Contribution to journalConference article

@article{94d305b7a9eb4452bc9ae5160fc81e77,
title = "ASYMPTOTIC AGREEMENT AND CONVERGENCE OF ASYNCHRONOUS STOCHASTIC ALGORITHMS.",
abstract = "Results on the convergence and asymptotic agreement of a class of asynchronous distributed algorithms which are in general time-varying, memory-dependent, and not necessarily associated with the optimization of a common cost functional are presented. It is shown that convergence and agreement can be reached by distributed learning and computation under a number of conditions, in which case a separation of fast and slow parts of the algorithm is possible, leading to a separation of the estimation part from the main algorithm.",
author = "Shu Li and Tamer Basar",
year = "1986",
month = "12",
day = "1",
language = "English (US)",
pages = "242--247",
journal = "Proceedings of the IEEE Conference on Decision and Control",
issn = "0191-2216",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - ASYMPTOTIC AGREEMENT AND CONVERGENCE OF ASYNCHRONOUS STOCHASTIC ALGORITHMS.

AU - Li, Shu

AU - Basar, Tamer

PY - 1986/12/1

Y1 - 1986/12/1

N2 - Results on the convergence and asymptotic agreement of a class of asynchronous distributed algorithms which are in general time-varying, memory-dependent, and not necessarily associated with the optimization of a common cost functional are presented. It is shown that convergence and agreement can be reached by distributed learning and computation under a number of conditions, in which case a separation of fast and slow parts of the algorithm is possible, leading to a separation of the estimation part from the main algorithm.

AB - Results on the convergence and asymptotic agreement of a class of asynchronous distributed algorithms which are in general time-varying, memory-dependent, and not necessarily associated with the optimization of a common cost functional are presented. It is shown that convergence and agreement can be reached by distributed learning and computation under a number of conditions, in which case a separation of fast and slow parts of the algorithm is possible, leading to a separation of the estimation part from the main algorithm.

UR - http://www.scopus.com/inward/record.url?scp=0022956707&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0022956707&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:0022956707

SP - 242

EP - 247

JO - Proceedings of the IEEE Conference on Decision and Control

JF - Proceedings of the IEEE Conference on Decision and Control

SN - 0191-2216

ER -