Adaptive Inertial Method

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Long, Han, He, Bingsheng, Ye, Yinyu, Zhang, Jiheng
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918028141133824
author Long, Han
He, Bingsheng
Ye, Yinyu
Zhang, Jiheng
author_facet Long, Han
He, Bingsheng
Ye, Yinyu
Zhang, Jiheng
contents In this paper, we introduce the Adaptive Inertial Method (AIM), a novel framework for accelerated first-order methods through a customizable inertial term. We provide a rigorous convergence analysis establishing a global convergence rate of O(1/k) under mild conditions, requiring only convexity and local Lipschitz differentiability of the objective function. Our method enables adaptive parameter selection for the inertial term without manual tuning. Furthermore, we derive the particular form of the inertial term that transforms AIM into a new Quasi-Newton method. Notably, under specific circumstances, AIM coincides with the regularized Newton method, achieving an accelerated rate of O(1/k^2) without Hessian inversions. Through extensive numerical experiments, we demonstrate that AIM exhibits superior performance across diverse optimization problems, highlighting its practical effectiveness.
format Preprint
id arxiv_https___arxiv_org_abs_2505_15114
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Adaptive Inertial Method
Long, Han
He, Bingsheng
Ye, Yinyu
Zhang, Jiheng
Optimization and Control
90C25, 90C30, 90C53, 65K10
In this paper, we introduce the Adaptive Inertial Method (AIM), a novel framework for accelerated first-order methods through a customizable inertial term. We provide a rigorous convergence analysis establishing a global convergence rate of O(1/k) under mild conditions, requiring only convexity and local Lipschitz differentiability of the objective function. Our method enables adaptive parameter selection for the inertial term without manual tuning. Furthermore, we derive the particular form of the inertial term that transforms AIM into a new Quasi-Newton method. Notably, under specific circumstances, AIM coincides with the regularized Newton method, achieving an accelerated rate of O(1/k^2) without Hessian inversions. Through extensive numerical experiments, we demonstrate that AIM exhibits superior performance across diverse optimization problems, highlighting its practical effectiveness.
title Adaptive Inertial Method
topic Optimization and Control
90C25, 90C30, 90C53, 65K10
url https://arxiv.org/abs/2505.15114