Almost sure convergence of randomly truncated stochastic algorithms under verifiable condi\-tions

DOI10.1016/J.SPL.2008.02.034MaRDI QIDQ952845zbMATH OpenOpenAlexFDO

Authors Jérôme Lelong

Publication date 14 November 2008

Published in Statistics \& Probability Letters (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/0706.0841

Mathematics Subject Classification ID

Stochastic approximation (62L20) Strong limit theorems (60F15)

Abstract: We study the almost sure convergence of randomly truncated stochastic algorithms. We present a new convergence theorem which extends the already known results by making vanish the classical condition on the noise terms. The aim of this work is to prove an almost sure convergence result of randomly truncated stochastic algorithms under easily verifiable conditions

Recommendations

• Asymptotic normality of randomly truncated stochastic algorithms
• Almost sure convergence of stochastic approximation algorithms with non-additive noise
• Stochastic approximation with random truncations, state-dependent noise and discontinuous dynamics
• Almost sure convergence of a class of stochastic algorithms
• Truncated stochastic approximation with moving bounds: convergence

Cites work

• scientific article; zbMATH DE number 3992716 (Why is no real title available?)
• A Stochastic Approximation Method
• Asymptotic study of stochastic algorithms and price calculations of Parisian options.
• Convergence and robustness of the Robbins-Monro algorithm truncated at randomly varying bounds
• Convergence of a stochastic approximation version of the EM algorithm
• General results on the convergence of stochastic algorithms
• Stochastic approximation and its applications
• Stochastic approximation methods for constrained and unconstrained systems

Cited in

(17)

• Robust adaptive importance sampling for normal random vectors
• Stochastic approximation with random truncations, state-dependent noise and discontinuous dynamics
• A Robbins-Monro procedure for estimation in semiparametric regression models
• Coupling importance sampling and multilevel Monte Carlo using sample average approximation
• A framework for adaptive Monte Carlo procedures
• Almost sure convergence of stochastic approximation algorithms with non-additive noise
• Some convergence theorems for RM algorithm
• Truncated stochastic approximation with moving bounds: convergence
• Almost sure convergence of a class of stochastic algorithms
• Some multivariate risk indicators: minimization by using a Kiefer-Wolfowitz approach to the mirror stochastic algorithm
• Importance sampling and statistical Romberg method
• Asymptotic normality of randomly truncated stochastic algorithms
• Asymptotic behavior of truncated stochastic approximation procedures
• Relative entropy minimization over Hilbert spaces via Robbins-Monro
• Rate of convergence of truncated stochastic approximation procedures with moving bounds
• Liquidity costs: a new numerical methodology and an empirical study
• Convergence of the Wang-Landau algorithm

This page was built for publication: Almost sure convergence of randomly truncated stochastic algorithms under verifiable condi\-tions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q952845)