The gradient projection algorithm for a~proximally smooth set and a~function with Lipschitz continuous gradient
Sbornik. Mathematics, Tome 211 (2020) no. 4, pp. 481-504
Voir la notice de l'article provenant de la source Math-Net.Ru
We consider the minimization problem for a nonconvex function with Lipschitz continuous gradient on a proximally smooth (possibly nonconvex) subset of a finite-dimensional Euclidean space. We introduce the error bound condition with exponent $\alpha\in(0,1]$ for the gradient mapping. Under this condition, it is shown that the standard gradient projection algorithm converges to a solution of the problem linearly or sublinearly, depending on the value of the exponent $\alpha$. This paper is theoretical.
Bibliography: 23 titles.
Keywords:
gradient mapping, error bound condition, proximal smoothness, nonconvex extremal problem.
Mots-clés : gradient projection algorithm
Mots-clés : gradient projection algorithm
@article{SM_2020_211_4_a0,
author = {M. V. Balashov},
title = {The gradient projection algorithm for a~proximally smooth set and a~function with {Lipschitz} continuous gradient},
journal = {Sbornik. Mathematics},
pages = {481--504},
publisher = {mathdoc},
volume = {211},
number = {4},
year = {2020},
language = {en},
url = {http://geodesic.mathdoc.fr/item/SM_2020_211_4_a0/}
}
TY - JOUR AU - M. V. Balashov TI - The gradient projection algorithm for a~proximally smooth set and a~function with Lipschitz continuous gradient JO - Sbornik. Mathematics PY - 2020 SP - 481 EP - 504 VL - 211 IS - 4 PB - mathdoc UR - http://geodesic.mathdoc.fr/item/SM_2020_211_4_a0/ LA - en ID - SM_2020_211_4_a0 ER -
M. V. Balashov. The gradient projection algorithm for a~proximally smooth set and a~function with Lipschitz continuous gradient. Sbornik. Mathematics, Tome 211 (2020) no. 4, pp. 481-504. http://geodesic.mathdoc.fr/item/SM_2020_211_4_a0/