Asymptotic behavior of truncated stochastic approximation procedures

被引：0

作者：

Sharia T. ^{[1
]}

Zhong L. ^{[1
]}

机构：

[1] Dept. of Math., Royal Holloway, Univ. of London, London

来源：

Mathematical Methods of Statistics | 2017年 / 26卷 / 1期

关键词：

parameter estimation; recursive estimation; stochastic approximation;

D O I：

10.3103/S1066530717010033

中图分类号：

学科分类号：

摘要：

We study asymptotic behavior 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 quitemild 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 formof the central limit theoremcan be applied to derive asymptotic distribution of the corresponding processes. The theory is illustrated by various examples and special cases. © 2017, Allerton Press, Inc.

引用

页码：37 / 54

页数：17

共 25 条

[1]

Andradottir S., A Stochastic Approximation Algorithm with Varying Bounds, Operations Res., 43, 6, pp. 1037-1048, (1995)

[2]

Benveniste A., Metivier M., Priouret P., Stochastic Approximations and Adaptive Algorithms, (1990)

[3]

Borkar V.S., Stochastic Approximation, (2008)

[4]

Chen H.F., Guo L., Gao A.J., Convergence and Robustness of the Robbins–Monro Algorithm Truncated at Randomly Varying Bounds, Stoch. Proc. and Their Appl., 27, pp. 217-231, (1987)

[5]

Chen H.F., Zhu Y.M., Stochastic Approximation Procedures with Randomly Varying Truncations, Scientia Sinica, Series A, Math. Phys. Astron. & Techn. Sci., 29, 9, pp. 914-926, (1986)

[6]

Cramer H., Mathematical Methods of Statistics, (1946)

[7]

Fabian V., On Asymptotically Efficient Recursive Estimation, Ann. Statist., pp. 854-866, (1978)

[8]

Kallenberg O., Foundations of Modern Probability, (2002)

[9]

Khas'minskii R.Z., Nevelson M.B., Stochastic Approximation and Recursive Estimation, (1972)

[10]

Kushner H.J., Stochastic Approximation: a Survey, Wiley Interdisciplinary Reviews: Computational Statistics, 2, 1, pp. 87-96, (2010)

← 1 2 3 →