On the Gradient Projection Method for Weakly Convex Functions on a Proximally Smooth Set
Matematičeskie zametki, Tome 108 (2020) no. 5, pp. 657-668
Voir la notice de l'article provenant de la source Math-Net.Ru
Let a weakly convex function (in the general case, nonconvex and nonsmooth) satisfy the quadratic growth condition. It is proved that the gradient projection method for minimizing such a function on a set converges with linear rate on a proximally smooth (nonconvex) set of special form (for example, on a smooth manifold), provided that the weak convexity constant of the function is less than the constant in the quadratic growth condition and the constant of proximal smoothness for the set is sufficiently large. The connection between the quadratic growth condition on the function and other conditions is discussed.
Keywords:
weak convexity, quadratic growth, gradient projection method, proximal smoothness, nonsmooth analysis.
@article{MZM_2020_108_5_a1,
author = {M. V. Balashov},
title = {On the {Gradient} {Projection} {Method} for {Weakly} {Convex} {Functions} on a {Proximally} {Smooth} {Set}},
journal = {Matemati\v{c}eskie zametki},
pages = {657--668},
publisher = {mathdoc},
volume = {108},
number = {5},
year = {2020},
language = {ru},
url = {http://geodesic.mathdoc.fr/item/MZM_2020_108_5_a1/}
}
TY - JOUR AU - M. V. Balashov TI - On the Gradient Projection Method for Weakly Convex Functions on a Proximally Smooth Set JO - Matematičeskie zametki PY - 2020 SP - 657 EP - 668 VL - 108 IS - 5 PB - mathdoc UR - http://geodesic.mathdoc.fr/item/MZM_2020_108_5_a1/ LA - ru ID - MZM_2020_108_5_a1 ER -
M. V. Balashov. On the Gradient Projection Method for Weakly Convex Functions on a Proximally Smooth Set. Matematičeskie zametki, Tome 108 (2020) no. 5, pp. 657-668. http://geodesic.mathdoc.fr/item/MZM_2020_108_5_a1/