A law of the iterated logarithm for stochastic approximation procedures in \(d\)-dimensional Euclidean space.

DOI10.1016/S0304-4149(03)00016-4zbMath1075.62072MaRDI QIDQ2574572

Rainer Schwabe, Valery Koval

Publication date: 29 November 2005

Published in: Stochastic Processes and their Applications (Search for Journal in Brave)

zbMATH Keywords

rate of convergence; stochastic approximation; law of the iterated logarithm

Mathematics Subject Classification ID

60F15: Strong limit theorems

62L20: Stochastic approximation

Related Items

The Compact Law of the Iterated Logarithm for Multivariate Stochastic Approximation Algorithms

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• A note on the almost sure central limit theorem
• On strong invariance principles under dependence assumptions
• Extensions of results of Komlós, Major, and Tusnády to the multivariate case
• Almost sure invariance principles for partial sums of mixing B-valued random variables
• Almost sure approximations to the Robbins-Monro and Kiefer-Wolfowitz processes with dependent noise
• Gaussian processes, moving averages and quick detection problems
• Approximation theorems for independent and weakly dependent random vectors
• Rate of convergence of stochastic approximation procedures in a Banach space
• On the almost sure asymptotic behaviour of stochastic algorithm
• Asymptotic normality for a vector stochastic difference equation with applications in stochastic approximation
• On Upper Functions for Stochastic Approximation Procedures
• Exact bounds for the rate of convergence in general stochastic approximation procedures
• An almost sure Invariance Principle for Hilbert Space Valued Martingales
• A new law of the iterated logarithm in \(R^d\) with application to matrix-normalized sums of random vectors