Approximation gaussienne d'algorithmes stochastiques à dynamique markovienne. (Gaussian approximation of stochastic algorithms)

MaRDI QIDQ1102035zbMATH OpenFDO

Authors Catherine Bouton

Publication date 1988

Published in Annales de l'Institut Henri Poincaré. Probabilités et Statistiques (Search for Journal in Brave)

Full work available at URL http://www.numdam.org/item?id=AIHPB_1988__24_1_131_0, https://eudml.org/doc/77316

zbMATH Keywords

asymptotic behaviourGaussian diffusionsmixing propertiesstochastic approximation algorithmstransition kernels

Mathematics Subject Classification ID

Gaussian processes (60G15) Signal detection and filtering (aspects of stochastic processes) (60G35) Stochastic approximation (62L20)

Review text

This paper addresses a problem involving a class of stochastic approximation algorithms. The author studies in fact the asymptotic behaviour of the ``normalized difference between a process built from the successive values produced by the algorithm and the solution of an ordinary differential equation ``naturally associated with it. Two theorems are given which, under appropriate but lengthy assumptions, insure that the normalized differences converge weakly towards Gaussian diffusions. The difference between the two theorems pertains to different behaviours assumed for the ``steps in the algorithms. The assumptions bear on the transition kernels of the Markov processes which ``drive the algorithms, rather than on moment and mixing properties of the random driving mechanism.

Recommendations

• scientific article; zbMATH DE number 3988541
• About Gaussian schemes in stochastic approximation
• scientific article; zbMATH DE number 721880
• On the convergence of markovian stochastic algorithms with rapidly decreasing ergodicity rates
• Convergence of a class of stochastic approximation procedures

Cited in

(15)

• A strong approximation theorem for stochastic recursive algorithms
• Weak convergence rates for stochastic approximation with application to multiple targets and simulated annealing
• About Gaussian schemes in stochastic approximation
• Smooth dependence and the rate of convergence of the stochastic algorithm maximizing Gaussian probability
• An optimal Gauss-Markov approximation for a process with stochastic drift and applications
• Nonlinear randomized urn models: a stochastic approximation viewpoint
• Central limit theorems for stochastic approximation with controlled Markov chain dynamics
• scientific article; zbMATH DE number 3881589 (Why is no real title available?)
• Randomized urn models revisited using stochastic approximation
• scientific article; zbMATH DE number 3988541 (Why is no real title available?)
• scientific article; zbMATH DE number 4044844 (Why is no real title available?)
• scientific article; zbMATH DE number 4104130 (Why is no real title available?)
• Sur quelques algorithmes récursifs pour les probabilités numériques
• Decreasing step Stochastic algorithms: a.s. behaviour of weighted empirical measures
• Self-organization and a.s. convergence of the one-dimensional Kohonen algorithm with non-uniformly distributed stimuli

This page was built for publication: Approximation gaussienne d'algorithmes stochastiques à dynamique markovienne. (Gaussian approximation of stochastic algorithms)

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1102035)