Guardado en:
Detalles Bibliográficos
Autores principales: Pan, Jianting, Yan, Ming
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2403.02861
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910711283712000
author Pan, Jianting
Yan, Ming
author_facet Pan, Jianting
Yan, Ming
contents This paper presents an algorithm tailored for the efficient recovery of sparse probability measures incorporating $\ell_0$-sparse regularization within the probability simplex constraint. Employing the Bregman proximal gradient method, our algorithm achieves sparsity by explicitly solving underlying subproblems. We rigorously establish the convergence properties of the algorithm, showcasing its capacity to converge to a local minimum with a convergence rate of $O(1/k)$ under mild assumptions. To substantiate the efficacy of our algorithm, we conduct numerical experiments, offering a compelling demonstration of its efficiency in recovering sparse probability measures.
format Preprint
id arxiv_https___arxiv_org_abs_2403_02861
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Efficient sparse probability measures recovery via Bregman gradient
Pan, Jianting
Yan, Ming
Optimization and Control
This paper presents an algorithm tailored for the efficient recovery of sparse probability measures incorporating $\ell_0$-sparse regularization within the probability simplex constraint. Employing the Bregman proximal gradient method, our algorithm achieves sparsity by explicitly solving underlying subproblems. We rigorously establish the convergence properties of the algorithm, showcasing its capacity to converge to a local minimum with a convergence rate of $O(1/k)$ under mild assumptions. To substantiate the efficacy of our algorithm, we conduct numerical experiments, offering a compelling demonstration of its efficiency in recovering sparse probability measures.
title Efficient sparse probability measures recovery via Bregman gradient
topic Optimization and Control
url https://arxiv.org/abs/2403.02861