Decreasing step Stochastic algorithms: a.s. behaviour of weighted empirical measures

DOI10.1515/MCMA.2002.8.3.237MaRDI QIDQ4792954zbMATH OpenOpenAlexFDO

Authors Jean-Claude Fort, Gilles Pagès

Publication date 30 September 2003

Published in Monte Carlo Methods and Applications (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1515/mcma.2002.8.3.237

zbMATH Keywords

parameter estimationcentral limit theoremstochastic approximationempirical distribution

Mathematics Subject Classification ID

Computational methods for stochastic equations (aspects of stochastic analysis) (60H35) Numerical solutions to stochastic differential and integral equations (65C30)

Recommendations

• scientific article; zbMATH DE number 1043533
• Rates of convergence of adaptive step-size of stochastic approximation algorithms
• Théorèmes de convergence presque sure pour une classe d'algorithmes stochastiques à pas decroissant
• scientific article; zbMATH DE number 3896700
• Approximation gaussienne d'algorithmes stochastiques à dynamique markovienne. (Gaussian approximation of stochastic algorithms)

Cited in

(5)

• Nonlinear randomized urn models: a stochastic approximation viewpoint
• When can the two-armed bandit algorithm be trusted?
• Behavior of the Euler scheme with decreasing step in a degenerate situation
• Stochastic recursive algorithms for optimization. Simultaneous perturbation methods
• How Fast Is the Bandit?

This page was built for publication: Decreasing step Stochastic algorithms: a.s. behaviour of weighted empirical measures

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4792954)