A Perturbed Gradient Algorithm in Hilbert Spaces

Kengy Barty (kengy.bartycermics.enpc.fr)
Jean-Sebastien Roy (jean-sebastien.royedf.fr)
Cyrille Strugarek (cyrille.strugarekedf.fr)

Abstract: We propose a perturbed gradient algorithm with stochastic noises to solve a general class of optimization problems. We provide a convergence proof for this algorithm, under classical assumptions on the descent direction, and new assumptions on the stochastic noises. Instead of requiring the stochastic noises to correspond to martingale increments, we only require these noises to be asymptotically so. Furthermore, the variance of these noises is allowed to grow infinitely under the control of a decreasing sequence linked with the gradient stepsizes. We then compare this new approach and assumptions with classical ones in the stochastic approximation literature. As an application of this general setting, we show how the algorithm to solve infinite dimensional stochastic optimization problems recently developped by the authors in another paper is a special case of the following perturbed gradient with stochastic noises.

Keywords: Stochastic Quasi-Gradient, Perturbed Gradient, Infinite Dimen-

Category 1: Stochastic Programming

Category 2: Convex and Nonsmooth Optimization (Convex Optimization )

Category 3: Applications -- OR and Management Sciences

Citation: Internal report--EDF R&D--February 2005

Download: [PDF]

Entry Submitted: 03/17/2005
Entry Accepted: 03/18/2005
Entry Last Modified: 05/19/2005

Modify/Update this entry