Moderate deviations for recursive stochastic algorithms

We prove a moderate deviation principle for the continuous time interpolation of discrete time recursive stochastic processes. The methods of proof are somewhat different from the corresponding large deviation result, and in particular the proof of the upper bound is more complicated.

Saved in:
Bibliographic Details
Published inStochastic systems Vol. 5; no. 1; pp. 87 - 119
Main Authors Paul Dupuis, Dane Johnson
Format Journal Article
LanguageEnglish
Published Institute for Operations Research and the Management Sciences (INFORMS) 01.12.2015
Subjects
Large deviations
moderate deviations
weak convergence
Online AccessGet full text
ISSN1946-5238
1946-5238
DOI10.1214/14-ssy138

Cover

More Information
Summary:We prove a moderate deviation principle for the continuous time interpolation of discrete time recursive stochastic processes. The methods of proof are somewhat different from the corresponding large deviation result, and in particular the proof of the upper bound is more complicated.
ISSN:1946-5238
1946-5238
DOI:10.1214/14-ssy138