Advanced search
Start date
Betweenand
Related content
(Reference retrieved automatically from Web of Science through information on FAPESP grant and its corresponding number as mentioned in the publication by the authors.)

String-averaging incremental stochastic subgradient algorithms

Full text
Author(s):
Oliveira, R. M. [1] ; Helou, E. S. [1] ; Costa, E. F. [1]
Total Authors: 3
Affiliation:
[1] Univ Sao Paulo, Dept Appl Math & Stat, Inst Math & Comp Sci, Sao Carlos, SP - Brazil
Total Affiliations: 1
Document type: Journal article
Source: OPTIMIZATION METHODS & SOFTWARE; v. 34, n. 3, p. 665-692, MAY 4 2019.
Web of Science Citations: 0
Abstract

We present a method to solve constrained convex stochastic optimization problems when the objective is a finite sum of convex functions . Our method is based on Incremental Stochastic Subgradient Algorithms and String-Averaging techniques, with an assumption that the subgradient directions are affected by random errors in each iteration. Our analysis allows the method to perform approximate projections onto the feasible set in each iteration. We provide convergence results for the case where a diminishing step-size rule is used. We test our method in a large set of random instances of a stochastic convex programming problem and we compare its performance with the robust mirror descent stochastic approximation algorithm proposed in Nemirovski et al. (Robust stochastic approximation approach to stochastic programming, SIAM J Optim 19 (2009), pp. 15741609). (AU)

FAPESP's process: 15/10171-2 - Incremental methods and String-Averaging for non-differentiable convex optimization with inaccurate Subgradients
Grantee:Rafael Massambone de Oliveira
Support type: Scholarships in Brazil - Doctorate
FAPESP's process: 13/19380-8 - Control and filtering of stochastic systems
Grantee:Eduardo Fontoura Costa
Support type: Regular Research Grants
FAPESP's process: 13/07375-0 - CeMEAI - Center for Mathematical Sciences Applied to Industry
Grantee:José Alberto Cuminato
Support type: Research Grants - Research, Innovation and Dissemination Centers - RIDC
FAPESP's process: 13/16508-3 - Fast computation of the generalized Backprojection operator with applications in tomographic image reconstruction
Grantee:Elias Salomão Helou Neto
Support type: Regular Research Grants
FAPESP's process: 17/20934-9 - Filtering and control of jump parameter systems
Grantee:Eduardo Fontoura Costa
Support type: Regular Research Grants