A stopping rule for stochastic approximation

• Takayuki Wada ^[1] ; Yasumasa Fujisaki ^[1]
  1. [1] Osaka University

     Osaka University

     Kita Ku, Japón

     
• Localización: Automatica: A journal of IFAC the International Federation of Automatic Control, ISSN 0005-1098, Vol. 60, 2015, págs. 1-6
• Idioma: inglés
• Texto completo no disponible (Saber más ...)
• Resumen

  • A stochastic approximation algorithm is a recursive procedure to find the solution to an unknown nonlinear equation via noisy measurements. In this paper, we present a stopping rule for a stochastic approximation. We show that there is a high probability that the distance between the exact solution and the candidate solution is less than a specified tolerance level when the stochastic approximation stops according to our stopping rule. Furthermore, the number of recursions required by the stopping rule is a polynomial function of the problem size.