• DocumentCode
    486072
  • Title

    Distributed Asynchronous Deterministic and Stochastic Gradient Optimization Algorithms

  • Author

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

  • Author_Institution
    Information Systems Laboratory, Stanford University, Stanford, CA 94305
  • fYear
    1984
  • fDate
    6-8 June 1984
  • Firstpage
    484
  • Lastpage
    489
  • 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.
  • Keywords
    Approximation algorithms; Convergence; Cost function; Delay effects; Distributed algorithms; Distributed computing; Iterative algorithms; Laboratories; Stochastic processes; Stochastic systems;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    American Control Conference, 1984
  • Conference_Location
    San Diego, CA, USA
  • Type

    conf

  • Filename
    4788427
    • Link To Document
    https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=486072