A Continuous Conditional Gradient Method
Yugoslav journal of operations research, Tome 9 (1999) no. 2, p. 169
Cet article a éte moissonné depuis la source eLibrary of Mathematical Institute of the Serbian Academy of Sciences and Arts
In this paper we study the continuous conditional gradient method to solve
convex minimization problems in Hilbert space. First , sufficient conditions for
convergence are provided and the convergence rate is found for a minimization
problem with a strong convex function. Then, the regularized method is considered for
a minimization problem with inaccurate initial data. Regularization is based on the
continuous conditional gradient method in conjunction with the penalty function
method. The sufficient conditions for the convergence of the regularized method are
presented, the regularizing operator is constructed, and a stopping rule for the
continuous process is proposed.
Classification :
90C25 90C52
Keywords: Continuous methods, conditional gradient, regularization.
Keywords: Continuous methods, conditional gradient, regularization.
@article{YJOR_1999_9_2_a1,
author = {Milojica Ja\'cimovi\'c and Andjelija Geary},
title = {A {Continuous} {Conditional} {Gradient} {Method}},
journal = {Yugoslav journal of operations research},
pages = {169 },
year = {1999},
volume = {9},
number = {2},
zbl = {1006.90061},
language = {en},
url = {http://geodesic.mathdoc.fr/item/YJOR_1999_9_2_a1/}
}
Milojica Jaćimović; Andjelija Geary. A Continuous Conditional Gradient Method. Yugoslav journal of operations research, Tome 9 (1999) no. 2, p. 169 . http://geodesic.mathdoc.fr/item/YJOR_1999_9_2_a1/