• DocumentCode
    2618707
  • Title

    Improved SPSA optimization algorithm requiring a single measurement per iteration

  • Author

    Alhabsi, Amer H.

  • Author_Institution
    Sultan Qaboos Univ., Al-Khod, Oman
  • fYear
    2010
  • fDate
    10-13 May 2010
  • Firstpage
    263
  • Lastpage
    265
  • Abstract
    The simultaneous perturbation stochastic approximation (SPSA) is a simple and effective optimization algorithm. It requires only two measurements of the objective function per iteration regardless of the dimension of the objective function. A modified SPSA algorithms is presented in this research. It requires a single measurement of the objective function per iteration. Application of the proposed algorithm are presented as well as some simulation results.
  • Keywords
    approximation theory; optimisation; perturbation techniques; stochastic processes; SPSA optimization algorithm; objective function per iteration; simultaneous perturbation stochastic approximation; single measurement per iteration; cost function; gradient estimation; optimization;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Information Sciences Signal Processing and their Applications (ISSPA), 2010 10th International Conference on
  • Conference_Location
    Kuala Lumpur
  • Print_ISBN
    978-1-4244-7165-2
  • Type

    conf

  • DOI
    10.1109/ISSPA.2010.5605476
  • Filename
    5605476
    • Link To Document
    https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=2618707