Moderate deviations for recursive stochastic algorithms

DOI10.1214/14-SSY138zbMATH Open1335.60050arXiv1401.6055MaRDI QIDQ3466705FDOQ3466705

Paul Dupuis, Dane Johnson

Publication date: 25 January 2016

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. The results can be applied to the design of accelerated Monte Carlo algorithms for certain problems, where schemes based on moderate deviations are easier to construct and in certain situations provide performance comparable to those based on large deviations.

Full work available at URL: https://arxiv.org/abs/1401.6055

Recommendations

• Moderate deviations for a class of recursions
• Moderate deviation principles for recursive regression estimators defined by stochastic approximation method
• Large and moderate deviation principles for nonparametric recursive kernel distribution estimators defined by stochastic approximation method
• Large and moderate deviation principles for recursive kernel density estimators defined by stochastic approximation method.
• Moderate deviation principles for nonparametric recursive distribution estimators using Bernstein polynomials

zbMATH Keywords

large deviationsweak convergencemoderate deviationsrecursive stochastic processes

Mathematics Subject Classification ID

Large deviations (60F10) Central limit and other weak theorems (60F05) Functional limit theorems; invariance principles (60F17) Discrete-time Markov processes on general state spaces (60J05) Limit theorems in probability theory (60F99)

Cites Work

• A variational representation for certain functionals of Brownian motion
• Averaging principle of SDE with small diffusion: Moderate deviations
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Importance Sampling, Large Deviations, and Differential Games
• Variational representations for continuous time processes
• Splitting for rare event simulation: A large deviation approach to design and analysis
• Moderate deviations for martingales with bounded jumps
• Moderate deviations for martingale differences and applications to φ -mixing sequences
• Subsolutions of an Isaacs Equation and Efficient Schemes for Importance Sampling
• On Lyapunov Inequalities and Subsolutions for Efficient Importance Sampling
• Large deviations and stochastic homogenization
• Moderate deviations for empirical measures of Markov chains: Upper bounds
• Moderate deviations for empirical measures of Markov chains: Lower bounds
• Moderate deviations of inhomogeneous functionals of Markov processes and application to averaging.
• Moderate deviations for martingales and mixing random processes
• M�langes d'�quations diff�rentielles et grands �carts � la loi des grands nombres
• Rough Limit Theorems on Large Deviations for Markov Stochastic Processes. IV

Cited In (8)

• Title not available (Why is that?)
• Inhomogeneous functionals and approximations of invariant distributions of ergodic diffusions: central limit theorem and moderate deviation asymptotics
• Moderate deviations for systems of slow-fast stochastic reaction-diffusion equations
• Large deviations analysis of some recursive algorithms with state dependent noise
• Large deviations for a class of recursive algorithms
• Importance sampling for stochastic reaction-diffusion equations in the moderate deviation regime
• Moderate deviations-based importance sampling for stochastic recursive equations
• Moderate Deviations and Invariance Principles for Sample Average Approximations

This page was built for publication: Moderate deviations for recursive stochastic algorithms

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3466705)