arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2604.00569math.OC
收藏

具有动量的加速近端束方法

An Accelerated Proximal Bundle Method with Momentum

Southern University of Science and Technology(南方科技大学);State Key Laboratory of Autonomous Intelligent Unmanned Systems(自主智能无人系统全国重点实验室);Southeast University(东南大学)

Zhuoqing Zheng, Junshan Yin, Shaofu Yang, Xuyang Wu

AI总结:

本文提出一种结合Nesterov动量的加速近端束方法,解决了传统近端束方法在光滑凸问题中收敛速率低的问题,实现最优O(1/k²)收敛性。

摘要:

近端束方法(PBM)是一类强大的凸优化算法。与梯度下降相比,PBM构建了更精确的替代模型,结合了多个过去迭代中的梯度和函数值,从而实现更快更稳健的收敛。然而,对于光滑凸问题,PBM仅能达到O(1/k)的收敛速率,这低于最优的O(1/k²)速率。为弥合这一差距,我们提出了一种加速近端束方法(APBM),将Nesterov的动量整合到PBM中。我们证明,在标准假设下,APBM达到最优的O(1/k²)收敛速率。数值实验展示了所提APBM的有效性。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑