DISTRIBUTED ASYNCHRONOUS DETERMINISTIC AND STOCHASTIC GRADIENT OPTIMIZATION ALGORITHMS.

John N. Tsitsiklis; Dimitri P. Bertsekas; Michael Athans

doi:10.23919/acc.1984.4788427

DISTRIBUTED ASYNCHRONOUS DETERMINISTIC AND STOCHASTIC GRADIENT OPTIMIZATION ALGORITHMS.

John N. Tsitsiklis, Dimitri P. Bertsekas, Michael Athans

Research output: Contribution to journal › Conference article › peer-review

19 Scopus citations

Abstract

We present a model for asynchronous distributed computation and analyze the convergence of natural asynchronous distributed versions of a large class of deterministic and stochastic gradient-like algorithms. We show that such algorithms retain the desirable convergence properties of their centralized counterparts, provided that the time between consecutive communications between processors plus communication delays are not too large.

Original language	English (US)
Pages (from-to)	484-489
Number of pages	6
Journal	Proceedings of the American Control Conference
Volume	1
DOIs	https://doi.org/10.23919/acc.1984.4788427
State	Published - 1984
Externally published	Yes

ASJC Scopus subject areas

Electrical and Electronic Engineering

Access to Document

10.23919/acc.1984.4788427

Cite this

@article{9dd45a17e7d441b9bf1c063368aba74b,

title = "DISTRIBUTED ASYNCHRONOUS DETERMINISTIC AND STOCHASTIC GRADIENT OPTIMIZATION ALGORITHMS.",

abstract = "We present a model for asynchronous distributed computation and analyze the convergence of natural asynchronous distributed versions of a large class of deterministic and stochastic gradient-like algorithms. We show that such algorithms retain the desirable convergence properties of their centralized counterparts, provided that the time between consecutive communications between processors plus communication delays are not too large.",

author = "Tsitsiklis, {John N.} and Bertsekas, {Dimitri P.} and Michael Athans",

year = "1984",

doi = "10.23919/acc.1984.4788427",

language = "English (US)",

volume = "1",

pages = "484--489",

journal = "Proceedings of the American Control Conference",

issn = "0743-1619",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - DISTRIBUTED ASYNCHRONOUS DETERMINISTIC AND STOCHASTIC GRADIENT OPTIMIZATION ALGORITHMS.

AU - Tsitsiklis, John N.

AU - Bertsekas, Dimitri P.

AU - Athans, Michael

PY - 1984

Y1 - 1984

N2 - We present a model for asynchronous distributed computation and analyze the convergence of natural asynchronous distributed versions of a large class of deterministic and stochastic gradient-like algorithms. We show that such algorithms retain the desirable convergence properties of their centralized counterparts, provided that the time between consecutive communications between processors plus communication delays are not too large.

AB - We present a model for asynchronous distributed computation and analyze the convergence of natural asynchronous distributed versions of a large class of deterministic and stochastic gradient-like algorithms. We show that such algorithms retain the desirable convergence properties of their centralized counterparts, provided that the time between consecutive communications between processors plus communication delays are not too large.

UR - http://www.scopus.com/inward/record.url?scp=0021619170&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0021619170&partnerID=8YFLogxK

U2 - 10.23919/acc.1984.4788427

DO - 10.23919/acc.1984.4788427

M3 - Conference article

AN - SCOPUS:0021619170

SN - 0743-1619

VL - 1

SP - 484

EP - 489

JO - Proceedings of the American Control Conference

JF - Proceedings of the American Control Conference

ER -

DISTRIBUTED ASYNCHRONOUS DETERMINISTIC AND STOCHASTIC GRADIENT OPTIMIZATION ALGORITHMS.

Abstract

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this