Projected Stochastic Gradients for Convex Constrained Problems in Hilbert Spaces

Geiersbach, C. & Pflug, G. ORCID: https://orcid.org/0000-0001-8215-3550 (2019). Projected Stochastic Gradients for Convex Constrained Problems in Hilbert Spaces. SIAM Journal on Optimization 29 (3) 2079-2099. 10.1137/18M1200208.

Full text not available from this repository.

Abstract

Convergence of a projected stochastic gradient algorithm is demonstrated for convex objective functionals with convex constraint sets in Hilbert spaces. In the convex case, the sequence of iterates un converges weakly to a point in the set of minimizers with probability one. In the strongly convex case, the sequence converges strongly to the unique optimum with probability one. An application to a class of PDE constrained problems with a convex objective, convex constraint, and random elliptic PDE constraints is shown. Theoretical results are demonstrated numerically.

Item Type:	Article
Research Programs:	Risk & Resilience (RISK)
Depositing User:	Luke Kirwan
Date Deposited:	28 Oct 2019 07:29
Last Modified:	27 Aug 2021 17:32
URI:	https://pure.iiasa.ac.at/16129

Actions (login required)

View Item