Almost sure convergence of randomly truncated stochastic algorithms under verifiable conditions

Jérôme Lelong (1)

1 CERMICS - Centre d'Enseignement et de Recherche en Mathématiques, Informatique et Calcul Scientifique

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

Mots clés: almost sure convergence; stochastic approximation; randomly truncated algorithms; almost sure convergence.

Domaines: Probabilités [math.PR]

Jérôme Lelong. Almost sure convergence of randomly truncated stochastic algorithms under verifiable conditions. Statistics and Probability Letters, 2008, 78 (16), pp.2632-2636. ⟨10.1016/j.spl.2008.02.034⟩. ⟨hal-00152255⟩