• DocumentCode
    2572037
  • Title

    A stopping rule for linear stochastic approximation

  • Author

    Wada, Takayuki ; Itani, Takamitsu ; Fujisaki, Yasumasa

  • Author_Institution
    Dept. of Syst. Sci., Kobe Univ., Nada, Japan
  • fYear
    2010
  • fDate
    15-17 Dec. 2010
  • Firstpage
    4171
  • Lastpage
    4176
  • Abstract
    A stopping rule is developed for multidimensional stochastic approximation which seeks for a solution of an unknown equation based on random noise corrupted residuals. It is assumed that the equation is linear, and the noise is independent and identically distributed random vectors with a bounded covariance. Then, it is shown that the necessary number of iterations is bounded by a polynomial of the covariance and parameters which specify probabilistic precision on the resultant candidate of the solution.
  • Keywords
    approximation theory; polynomials; random noise; stochastic processes; vectors; bounded covariance; covariance polynomial; distributed random vectors; linear stochastic approximation; random noise; stopping rule; Approximation algorithms; Approximation methods; Convergence; Equations; Estimation error; Noise; Probabilistic logic;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Decision and Control (CDC), 2010 49th IEEE Conference on
  • Conference_Location
    Atlanta, GA
  • ISSN
    0743-1546
  • Print_ISBN
    978-1-4244-7745-6
  • Type

    conf

  • DOI
    10.1109/CDC.2010.5717389
  • Filename
    5717389
    • Link To Document
    https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=2572037