Volume 8, Issue 1
Convergence Speed and Asymptotic Distribution of a Parallel Robbins-Monro Method

Yun-Min Zhu & Gang Yin

DOI:

J. Comp. Math., 8 (1990), pp. 45-54

Published online: 1990-08

Preview Full PDF 417 1995
Export citation
  • Abstract

Very recently, there is a growing interest in studying parallel and distributed stochastic approximation algorithms. Previously, we suggest such an algorithm to find zeros or locate maximum values of a regression function with large state space dimension in[1], and derived the strong consistency property for that algorithm. In the present work, we concern ourselves with the problem of asympotic properties of such an algorithm. We will study the limit behavior of the algorithm and obtain the rate of convergence and asymptotic normality results.

  • Keywords

  • AMS Subject Headings

  • Copyright

COPYRIGHT: © Global Science Press

  • Email address
  • BibTex
  • RIS
  • TXT
@Article{JCM-8-45, author = {}, title = {Convergence Speed and Asymptotic Distribution of a Parallel Robbins-Monro Method}, journal = {Journal of Computational Mathematics}, year = {1990}, volume = {8}, number = {1}, pages = {45--54}, abstract = { Very recently, there is a growing interest in studying parallel and distributed stochastic approximation algorithms. Previously, we suggest such an algorithm to find zeros or locate maximum values of a regression function with large state space dimension in[1], and derived the strong consistency property for that algorithm. In the present work, we concern ourselves with the problem of asympotic properties of such an algorithm. We will study the limit behavior of the algorithm and obtain the rate of convergence and asymptotic normality results. }, issn = {1991-7139}, doi = {https://doi.org/}, url = {http://global-sci.org/intro/article_detail/jcm/9418.html} }
TY - JOUR T1 - Convergence Speed and Asymptotic Distribution of a Parallel Robbins-Monro Method JO - Journal of Computational Mathematics VL - 1 SP - 45 EP - 54 PY - 1990 DA - 1990/08 SN - 8 DO - http://doi.org/ UR - https://global-sci.org/intro/article_detail/jcm/9418.html KW - AB - Very recently, there is a growing interest in studying parallel and distributed stochastic approximation algorithms. Previously, we suggest such an algorithm to find zeros or locate maximum values of a regression function with large state space dimension in[1], and derived the strong consistency property for that algorithm. In the present work, we concern ourselves with the problem of asympotic properties of such an algorithm. We will study the limit behavior of the algorithm and obtain the rate of convergence and asymptotic normality results.
Yun-Min Zhu & Gang Yin. (1970). Convergence Speed and Asymptotic Distribution of a Parallel Robbins-Monro Method. Journal of Computational Mathematics. 8 (1). 45-54. doi:
Copy to clipboard
The citation has been copied to your clipboard