An Accelerated Proximal Bundle Method with Momentum

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Zheng, Zhuoqing, Yin, Junshan, Yang, Shaofu, Wu, Xuyang
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908930423128064
author Zheng, Zhuoqing
Yin, Junshan
Yang, Shaofu
Wu, Xuyang
author_facet Zheng, Zhuoqing
Yin, Junshan
Yang, Shaofu
Wu, Xuyang
contents Proximal bundle methods (PBM) are a powerful class of algorithms for convex optimization. Compared to gradient descent, PBM constructs more accurate surrogate models that incorporate gradients and function values from multiple past iterations, which leads to faster and more robust convergence. However, for smooth convex problems, PBM only achieves an O(1/k) convergence rate, which is inferior to the optimal O(1/k^2) rate. To bridge this gap, we propose an accelerated proximal bundle method (APBM) that integrates Nesterov's momentum into PBM. We prove that under standard assumptions, APBM achieves the optimal O(1/k^2) convergence rate. Numerical experiments demonstrate the effectiveness of the proposed APBM.
format Preprint
id arxiv_https___arxiv_org_abs_2604_00569
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle An Accelerated Proximal Bundle Method with Momentum
Zheng, Zhuoqing
Yin, Junshan
Yang, Shaofu
Wu, Xuyang
Optimization and Control
Proximal bundle methods (PBM) are a powerful class of algorithms for convex optimization. Compared to gradient descent, PBM constructs more accurate surrogate models that incorporate gradients and function values from multiple past iterations, which leads to faster and more robust convergence. However, for smooth convex problems, PBM only achieves an O(1/k) convergence rate, which is inferior to the optimal O(1/k^2) rate. To bridge this gap, we propose an accelerated proximal bundle method (APBM) that integrates Nesterov's momentum into PBM. We prove that under standard assumptions, APBM achieves the optimal O(1/k^2) convergence rate. Numerical experiments demonstrate the effectiveness of the proposed APBM.
title An Accelerated Proximal Bundle Method with Momentum
topic Optimization and Control
url https://arxiv.org/abs/2604.00569