arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1611.06752math.STstat.TH
收藏

截断随机逼近过程的渐近性

Asymptotic Behaviour of Truncated Stochastic Approximation Procedures

Teo Sharia, Lei Zhong

摘要:

我们研究了具有三个主要特征的随机逼近过程的渐近行为:随机移动界截断,矩阵值随机步长序列,以及动态变化的随机回归函数。特别是,我们证明了在相当温和的条件下,随机逼近程序在统计意义上是渐近线性的,也就是说,它们可以表示为随机变量的加权和。因此,适当形式的中心极限定理可以用来导出相应过程的渐近分布。该理论通过各种例子和特殊情况来说明。

英文摘要:

We study asymptotic behaviour of stochastic approximation procedures with three main characteristics: truncations with random moving bounds, a matrix valued random step-size sequence, and a dynamically changing random regression function. In particular, we show that under quite mild conditions, stochastic approximation procedures are asymptotically linear in the statistical sense, that is, they can be represented as weighted sums of random variables. Therefore, a suitable form of the central limit theorem can be applied to derive asymptotic distribution of the corresponding processes. The theory is illustrated by various examples and special cases.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑