Open Access
2015 Moderate deviations for recursive stochastic algorithms
Paul Dupuis, Dane Johnson
Stoch. Syst. 5(1): 87-119 (2015). DOI: 10.1214/14-SSY138

Abstract

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.

Citation

Download Citation

Paul Dupuis. Dane Johnson. "Moderate deviations for recursive stochastic algorithms." Stoch. Syst. 5 (1) 87 - 119, 2015. https://doi.org/10.1214/14-SSY138

Information

Received: 1 January 2014; Published: 2015
First available in Project Euclid: 23 December 2015

zbMATH: 1335.60050
MathSciNet: MR3442390
Digital Object Identifier: 10.1214/14-SSY138

Subjects:
Primary: 60F10 , 60J05
Secondary: 60F17

Keywords: large deviations , Moderate deviations , weak convergence

Rights: Copyright © 2015 INFORMS Applied Probability Society

Vol.5 • No. 1 • 2015
Back to Top