GLL-type Nonmonotone Descent Methods Revisited under Kurdyka-Łojasiewicz Property

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Qian, Yitian, Tao, Ting, Pan, Shaohua, Qi, Houduo
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910911982206976
author Qian, Yitian
Tao, Ting
Pan, Shaohua
Qi, Houduo
author_facet Qian, Yitian
Tao, Ting
Pan, Shaohua
Qi, Houduo
contents The purpose of this paper is to extend the full convergence results of the classic GLL-type (Grippo-Lampariello-Lucidi) nonmonotone methods to nonconvex and nonsmooth optimization. We propose a novel iterative framework for the minimization of a proper and lower semicontinuous function $Φ$. The framework consists of the GLL-type nonmonotone decrease condition for a sequence, a relative error condition for its augmented sequence with respect to a Kurdyka-Łojasiewicz (KL) function $Θ$, and a relative gap condition for the partial maximum objective value sequence. The last condition is shown to be a product of the prox-regularity of $Φ$ on the set of cluster points, and to hold automatically under a mild condition on the objective value sequence. We prove that for any sequence and its bounded augmented sequence together falling within the framework, the sequence itself is convergent. Furthermore, when $Θ$ is a KL function of exponent $θ\in(0, 1)$, the convergence admits a linear rate if $θ\in(0, 1/2]$ and a sublinear rate if $θ\in(1/2, 1)$. As applications, we prove, for the first time, that the two existing algorithms, namely the nonmonotone proximal gradient (NPG) method with majorization and NPG with extrapolation both enjoy the full convergence of the iterate sequences for nonconvex and nonsmooth KL composite optimization problems.
format Preprint
id arxiv_https___arxiv_org_abs_2504_11385
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GLL-type Nonmonotone Descent Methods Revisited under Kurdyka-Łojasiewicz Property
Qian, Yitian
Tao, Ting
Pan, Shaohua
Qi, Houduo
Optimization and Control
90C26, 65K05, 49M27
The purpose of this paper is to extend the full convergence results of the classic GLL-type (Grippo-Lampariello-Lucidi) nonmonotone methods to nonconvex and nonsmooth optimization. We propose a novel iterative framework for the minimization of a proper and lower semicontinuous function $Φ$. The framework consists of the GLL-type nonmonotone decrease condition for a sequence, a relative error condition for its augmented sequence with respect to a Kurdyka-Łojasiewicz (KL) function $Θ$, and a relative gap condition for the partial maximum objective value sequence. The last condition is shown to be a product of the prox-regularity of $Φ$ on the set of cluster points, and to hold automatically under a mild condition on the objective value sequence. We prove that for any sequence and its bounded augmented sequence together falling within the framework, the sequence itself is convergent. Furthermore, when $Θ$ is a KL function of exponent $θ\in(0, 1)$, the convergence admits a linear rate if $θ\in(0, 1/2]$ and a sublinear rate if $θ\in(1/2, 1)$. As applications, we prove, for the first time, that the two existing algorithms, namely the nonmonotone proximal gradient (NPG) method with majorization and NPG with extrapolation both enjoy the full convergence of the iterate sequences for nonconvex and nonsmooth KL composite optimization problems.
title GLL-type Nonmonotone Descent Methods Revisited under Kurdyka-Łojasiewicz Property
topic Optimization and Control
90C26, 65K05, 49M27
url https://arxiv.org/abs/2504.11385