On the Acceleration of Proximal Bundle Methods
On the Acceleration of Proximal Bundle Methods
The proximal bundle method (PBM) is a fundamental and computationally effective algorithm for solving nonsmooth optimization problems. In this paper, we present the first variant of the PBM for smooth objectives, achieving an accelerated convergence rate of $O(\epsilon^{-1/2}\log(1/\epsilon))$, where $\epsilon$ is the desired accuracy. Our approach addresses an open question regarding the convergence guarantee of proximal bundle type methods, which was previously posed in two recent papers. We interpret the PBM as a proximal point algorithm and base our proposed algorithm on an accelerated inexact proximal point scheme. Our variant introduces a novel null step test and oracle while maintaining the core structure of the original algorithm. The newly proposed oracle substitutes the traditional cutting planes with a smooth lower approximation of the true function. We show that this smooth interpolating lower model can be computed as a convex quadratic program. We also examine a second setting where Nesterov acceleration can be effectively applied, specifically when the objective is the sum of a smooth function and a piecewise linear one.
David Fersztand、Xu Andy Sun
数学计算技术、计算机技术
David Fersztand,Xu Andy Sun.On the Acceleration of Proximal Bundle Methods[EB/OL].(2025-04-28)[2025-06-07].https://arxiv.org/abs/2504.20351.点此复制
评论