✦ LIBER ✦

An Almost Sure Central Limit Theorem for Stochastic Approximation Algorithms

✍ Scribed by Mariane Pelletier

Publisher: Elsevier Science
Year: 1999
Tongue: English
Weight: 154 KB
Volume: 71
Category: Article
ISSN: 0047-259X
DOI: 10.1006/jmva.1999.1830

No coin nor oath required. For personal study only.

✦ Synopsis

We prove an almost sure central limit theorem for some multidimensional stochastic algorithms used for the search of zeros of a function and known to satisfy a central limit theorem. The almost sure version of the central limit theorem requires either a logarithmic empirical mean (in the same way as in the case of independent identically distributed variables) or another scale, depending on the choice of the algorithm gains.

📜 SIMILAR VOLUMES

Almost sure central limit theorems for r

Almost sure central limit theorems for random fields

✍ István Fazekas; Zdzisław Rychlik 📂 Article 📅 2003 🏛 John Wiley and Sons 🌐 English ⚖ 133 KB 👁 1 views

## Abstract A general almost sure limit theorem is presented for random fields. It is applied to obtain almost sure versions of some (functional) central limit theorems. (© 2003 WILEY‐VCH Verlag GmbH & Co. KGaA, Weinheim)

Almost sure central limit theorem for pa

Almost sure central limit theorem for partial sums and maxima

✍ Peng Zuoxiang; Wang Lili; Saralees Nadarajah 📂 Article 📅 2009 🏛 John Wiley and Sons 🌐 English ⚖ 107 KB 👁 1 views

## Abstract Let __X__, __X__~1~, __X__~2~, … be i.i.d. random variables with nondegenerate common distribution function __F__, satisfying __EX__ = 0, __EX__^2^ = 1. Let __X~i~__ and __M~n~__ = max{__X~i~__, 1 ≤ __i__ ≤ __n__ }. Suppose there exists constants __a~n~__ > 0, __b~n~__ ∈ __R__ and a non

On the almost sure central limit theorem

On the almost sure central limit theorem for randomly indexed sums

✍ A. Krajka; J. Wasiura 📂 Article 📅 2009 🏛 John Wiley and Sons 🌐 English ⚖ 169 KB 👁 1 views

## Abstract Let {__S~n~__, __n__ ≥ 1} be partial sums of independent identically distributed random variables. The almost sure version of CLT is generalized on the case of randomly indexed sums {__S~Nn~__, __n__ ≥ 1}, where {__N~n~__, __n__ ≥ 1} is a sequence of positive integer‐valued random varia