Hostname: page-component-7b7567c8c-fvjsw Total loading time: 0 Render date: 2026-11-16T02:28:27.463Z Has data issue: false hasContentIssue false

Convergence of stochastic algorithms: from the Kushner–Clark theorem to the Lyapounov functional method

Published online by Cambridge University Press:  01 July 2016

Jean-Claude Fort*
Affiliation:
Université de Nancy 1 and Université de Paris 1
Gilles Pagès*
Affiliation:
Université Pierre et Marie Curie and Université de Paris 12
*
∗ Postal address: Université de Nancy I, Fac. Sciences, Dpt de Math., B.P. 239, F-54506 Vandoeuvre-Lès-Nancy Cedex, France and SAMOS, Université de Paris 1, UFR 27, 90, rue de Tolbiac F-75634 Paris Cedex 13, France.
∗∗ Postal address: Laboratoire de Probabilités, URA 224, Université P. et M. Curie, Pl. Jussieu, F-75252 Paris Cedex 05, France and Université de Paris XII, UFR, Sciences, 61 av. du Gal de Gaulle, 94010 Créteil Cedex, France.

Abstract

In the first part of this paper a global Kushner–Clark theorem about the convergence of stochastic algorithms is proved: we show that, under some natural assumptions, one can ‘read' from the trajectories of its ODE whether or not an algorithm converges. The classical stochastic optimization results are included in this theorem. In the second part, the above smoothness assumption on the mean vector field of the algorithm is relaxed using a new approach based on a path-dependent Lyapounov functional. Several applications, for non-smooth mean vector fields and/or bounded Lyapounov function settings, are derived. Examples and simulations are provided that illustrate and enlighten the field of application of the theoretical results.

Information

Type
General Applied Probability
Copyright
Copyright © Applied Probability Trust 1996 

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

Article purchase

Temporarily unavailable