Constrained Optimization via Stochastic approximation with a simultaneous perturbation gradient approximation.

Payman Sadegh

    Research output: Contribution to journalJournal articleResearchpeer-review

    Abstract

    This paper deals with a projection algorithm for stochastic approximation using simultaneous perturbation gradient approximation for optimization under inequality constraints where no direct gradient of the loss function is available and the inequality constraints are given as explicit functions of the optimization parameters. It is shown that, under application of the projection algorithm, the parameter iterate converges almost surely to a Kuhn-Tucker point, The procedure is illustrated by a numerical example, (C) 1997 Elsevier Science Ltd.
    Original languageEnglish
    JournalAutomatica
    Volume33
    Issue number5
    Pages (from-to)889-892
    ISSN0005-1098
    DOIs
    Publication statusPublished - May 1997

    Keywords

    • optimization
    • stochastic approximation
    • SPSA
    • constraints
    • Kuhn-Tucker point

    Fingerprint

    Dive into the research topics of 'Constrained Optimization via Stochastic approximation with a simultaneous perturbation gradient approximation.'. Together they form a unique fingerprint.

    Cite this