Some guidelines for using iterate averaging in stochastic approximation

被引:0
|
作者
Maryak, JL [1 ]
机构
[1] Johns Hopkins Univ, Appl Phys Lab, Laurel, MD 20723 USA
关键词
stochastic approximation; iterate averaging; mean square error; finite-difference stochastic approximation; simultaneous perturbation stochastic approximation;
D O I
暂无
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Averaging of the output (iterates) from a stochastic approximation (SA) recursion has been shown to be a useful technique for the gradient-based Robbins-Monro, form of SA. For the gradient-free (e.g., Kiefer-Wolfowitz) form, iterate averaging can produce an improvement in the stability of the algorithm and competitive mean-square errors relative to the standard (unaveraged) recursion. We discuss guidelines on how and when to use averaging in this context.
引用
收藏
页码:2287 / 2290
页数:4
相关论文
共 50 条