Work

Distributed Asynchronous Deterministic and Stochastic Gradient Optimization Algorithms

Year: 1984

Type: conference-paper

Abstract: We present a model for asynchronous distributed computation and then proceed to 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.

Source: Proceedings of the ... American Control Conference/Proceedings of the American Control Conference

DOI: 10.23919/acc.1984.4788427

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

Institutions: Stanford University, Massachusetts Institute of Technology

Language: English

Topic: Distributed Control Multi-Agent Systems

Subfield: Control and Systems Engineering

Field: Engineering

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W1528719522

FWCI:

Cites: 8

Cited by: 89

Related to: 10