Explicit Global Convergence Rates of BFGS without Line Search

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yu, Jianjiang, Gao, Weiguo, Luo, Luo
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918148925554688
author Yu, Jianjiang
Gao, Weiguo
Luo, Luo
author_facet Yu, Jianjiang
Gao, Weiguo
Luo, Luo
contents This paper studies the convergence rates of the Broyden--Fletcher--Goldfarb--Shanno~(BFGS) method without line search. We show that the BFGS method with an adaptive step size [Gao and Goldfarb, Optimization Methods and Software, 34(1):194-217, 2019] exhibits a two-phase non-asymptotic global convergence behavior when minimizing a strongly convex function, i.e., a linear convergence rate of $\mathcal{O}((1 - 1 / \varkappa)^{k})$ in the first phase and a superlinear convergence rate of $\mathcal{O}((\varkappa / k)^{k})$ in the second phase, where $k$ is the iteration counter and $\varkappa$ is the condition number. In contrast, the existing analysis only establishes asymptotic results. Furthermore, we propose a novel adaptive BFGS method without line search, which allows a larger step size by taking the gradient Lipschitz continuity into the algorithm design. We prove that our method achieves faster convergence when the initial point is far away from the optimal solution.
format Preprint
id arxiv_https___arxiv_org_abs_2509_22508
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Explicit Global Convergence Rates of BFGS without Line Search
Yu, Jianjiang
Gao, Weiguo
Luo, Luo
Optimization and Control
This paper studies the convergence rates of the Broyden--Fletcher--Goldfarb--Shanno~(BFGS) method without line search. We show that the BFGS method with an adaptive step size [Gao and Goldfarb, Optimization Methods and Software, 34(1):194-217, 2019] exhibits a two-phase non-asymptotic global convergence behavior when minimizing a strongly convex function, i.e., a linear convergence rate of $\mathcal{O}((1 - 1 / \varkappa)^{k})$ in the first phase and a superlinear convergence rate of $\mathcal{O}((\varkappa / k)^{k})$ in the second phase, where $k$ is the iteration counter and $\varkappa$ is the condition number. In contrast, the existing analysis only establishes asymptotic results. Furthermore, we propose a novel adaptive BFGS method without line search, which allows a larger step size by taking the gradient Lipschitz continuity into the algorithm design. We prove that our method achieves faster convergence when the initial point is far away from the optimal solution.
title Explicit Global Convergence Rates of BFGS without Line Search
topic Optimization and Control
url https://arxiv.org/abs/2509.22508