General multilevel adaptations for stochastic approximation algorithms. II: CLTs

DOI10.1016/J.SPA.2020.11.001MaRDI QIDQ1994904zbMATH OpenOpenAlexFDO

Authors Steffen Dereich

Publication date 18 February 2021

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

Full work available at URL https://arxiv.org/abs/1912.08130

zbMATH Keywords

central limit theorem (CLT)multilevel Monte CarloRuppert-Polyak averagestable convergencestochastic approximation

Mathematics Subject Classification ID

Central limit and other weak theorems (60F05) Discrete-time Markov processes on general state spaces (60J05) Stochastic approximation (62L20) Monte Carlo methods (65C05)

Abstract: In this article we establish central limit theorems for multilevel Polyak-Ruppert averaged stochastic approximation schemes. We work under very mild technical assumptions and consider the slow regime in wich typical errors decay like $N^{-delta}$ with $deltain(0,frac12)$ and the critical regime in which errors decay of order $N^{-1/2}sqrtlogN$ in the runtime $N$ of the algorithm.

Recommendations

• General multilevel adaptations for stochastic approximation algorithms of Robbins-Monro and Polyak-Ruppert type
• An almost sure central limit theorem for stochastic approximation algorithms
• Central limit theorems for stochastic approximation with controlled Markov chain dynamics
• Asymptotic Efficiency of Perturbation-Analysis-Based Stochastic Approximation with Averaging
• scientific article; zbMATH DE number 125286

Cites work

• A general method for debiasing a Monte Carlo estimator
• A generalization of the averaging procedure: the use of two-time-scale algorithms
• A Stochastic Approximation Method
• Acceleration of Stochastic Approximation by Averaging
• Almost sure approximations to the Robbins-Monro and Kiefer-Wolfowitz processes with dependent noise
• Asymptotic Distribution of Stochastic Approximation Procedures
• Central limit theorem for the multilevel Monte Carlo Euler method
• Expansion of the global error for numerical schemes solving stochastic differential equations
• General multilevel adaptations for stochastic approximation algorithms of Robbins-Monro and Polyak-Ruppert type
• scientific article; zbMATH DE number 3723610 (Why is no real title available?)
• scientific article; zbMATH DE number 48727 (Why is no real title available?)
• scientific article; zbMATH DE number 1972910 (Why is no real title available?)
• Multi-level stochastic approximation algorithms
• Multilevel Monte Carlo for Lévy-driven SDEs: central limit theorems for adaptive Euler schemes
• Multilevel Monte Carlo Path Simulation
• Stochastic algorithms
• Unbiased estimation with square root convergence for SDE models

Cited in

(6)

• General multilevel adaptations for stochastic approximation algorithms of Robbins-Monro and Polyak-Ruppert type
• Robbins-Monro algorithm with \(\psi\)-mixing random errors
• Central limit theorems for stochastic approximation with controlled Markov chain dynamics
• Large deviations principle for the Adaptive Multilevel Splitting Algorithm in an idealized setting
• Central limit theorems for stochastic gradient descent with averaging for stable manifolds
• Multi-index antithetic stochastic gradient algorithm

This page was built for publication: General multilevel adaptations for stochastic approximation algorithms. II: CLTs

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1994904)