Guardado en:
Detalles Bibliográficos
Autores principales: He, Jiahuan, Kan, Chao, Song, Wen
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:https://arxiv.org/abs/2312.11168
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911871267766272
author He, Jiahuan
Kan, Chao
Song, Wen
author_facet He, Jiahuan
Kan, Chao
Song, Wen
contents In this paper, we focus on the exploration of solution uniqueness, sharpness, and robust recovery in sparse regularization with a gauge $J$. Based on the criteria for the uniqueness of Lagrange multipliers in the dual problem, we give a characterization of the unique solution via the so-called radial cone. We establish characterizations of the isolated calmness (i.e., uniqueness of solutions combined with the calmness properties) of two types of the solution mappings and prove that they are equivalent under the assumption of metric subregularity of the subdifferentials for regularizers. Furthermore, we present sufficient and necessary conditions for a sharp solution, and show that these conditions guarantee robust recovery with a linear rate and imply local upper Lipschitzian properties of the solution mapping. Some applications of the polyhedral regularizer case such as sparse analysis regularization, weighted sorted $\ell_1$-norm sparse regularization, and non-polyhedral regularizer cases such as nuclear norm optimization, conic gauge optimization, and semidefinite conic gauge optimization are given.
format Preprint
id arxiv_https___arxiv_org_abs_2312_11168
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle On Solution Uniqueness and Robust Recovery for Sparse Regularization with a Gauge: from Dual Point of View
He, Jiahuan
Kan, Chao
Song, Wen
Optimization and Control
90C25, 90C46, 90C05, 65K05
In this paper, we focus on the exploration of solution uniqueness, sharpness, and robust recovery in sparse regularization with a gauge $J$. Based on the criteria for the uniqueness of Lagrange multipliers in the dual problem, we give a characterization of the unique solution via the so-called radial cone. We establish characterizations of the isolated calmness (i.e., uniqueness of solutions combined with the calmness properties) of two types of the solution mappings and prove that they are equivalent under the assumption of metric subregularity of the subdifferentials for regularizers. Furthermore, we present sufficient and necessary conditions for a sharp solution, and show that these conditions guarantee robust recovery with a linear rate and imply local upper Lipschitzian properties of the solution mapping. Some applications of the polyhedral regularizer case such as sparse analysis regularization, weighted sorted $\ell_1$-norm sparse regularization, and non-polyhedral regularizer cases such as nuclear norm optimization, conic gauge optimization, and semidefinite conic gauge optimization are given.
title On Solution Uniqueness and Robust Recovery for Sparse Regularization with a Gauge: from Dual Point of View
topic Optimization and Control
90C25, 90C46, 90C05, 65K05
url https://arxiv.org/abs/2312.11168