A functional central limit theorem for martingales in C(K) and its application to sequential estimates.
A New Sequential Design Based on the Robbins-Monro Procedure.
A note on confidence intervals for the Kiefer-Wolfowitz problem
A penalized bandit algorithm.
An extension of Driml-Nedoma continuous stochastic approximation procedure
Application de l'approximation stochastique à la détermination des masques pour la lecture automatique de caractères imprimés
Approximate maximum likelihood estimation for a spatial point pattern.
Several authors have proposed stochastic and non-stochastic approximations to the maximum likelihood estimate for a spatial point pattern. This approximation is necessary because of the difficulty of evaluating the normalizing constant. However, it appears to be neither a general theory which provides grounds for preferring a particular method, nor any extensive empirical comparisons. In this paper, we review five general methods based on approximations to the maximum likelihood estimate which have...
Approximation gaussienne d'algorithmes stochastiques à dynamique markovienne
Approximation par des intégrales de Stieltjes-Lebesgue d’intégrales stochastiques relatives au mouvement brownien indexé par
Approximation par des intégrales de Stieltjes-Lebesgue d’intégrales stochastiques relatives au mouvement brownien indexé par
Asymptotic normality of randomly truncated stochastic algorithms
We study the convergence rate of randomly truncated stochastic algorithms, which consist in the truncation of the standard Robbins–Monro procedure on an increasing sequence of compact sets. Such a truncation is often required in practice to ensure convergence when standard algorithms fail because the expected-value function grows too fast. In this work, we give a self contained proof of a central limit theorem for this algorithm under local assumptions on the expected-value function, which are fairly...
Bibliography on stochastic approximation
Continuous stochastic approximation procedure for evaluating the point at which the regression function stops to be non-positive
Convergence presque sûre et en moyenne des processus d'approximation stochastique, (1ère Partie) processus de Dvoretzky
Coupling a stochastic approximation version of EM with an MCMC procedure
The stochastic approximation version of EM (SAEM) proposed by Delyon et al. (1999) is a powerful alternative to EM when the E-step is intractable. Convergence of SAEM toward a maximum of the observed likelihood is established when the unobserved data are simulated at each iteration under the conditional distribution. We show that this very restrictive assumption can be weakened. Indeed, the results of Benveniste et al. for stochastic approximation with markovian perturbations are used to establish...
Coupling a stochastic approximation version of EM with an MCMC procedure
The stochastic approximation version of EM (SAEM) proposed by Delyon et al. (1999) is a powerful alternative to EM when the E-step is intractable. Convergence of SAEM toward a maximum of the observed likelihood is established when the unobserved data are simulated at each iteration under the conditional distribution. We show that this very restrictive assumption can be weakened. Indeed, the results of Benveniste et al. for stochastic approximation with Markovian perturbations are used to establish...
Dynamics of stochastic approximation algorithms
Efficiency of the Stochastic Approximation Method
Erratum : “Pathwise approximations of process based on the fine structure of their filtrations”
Estimation and annealing for Gibbsian fields