Practical Regularized Quasi-Newton Methods with Inexact Function Values

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Hamaguchi, Hiroki, Marumo, Naoki, Takeda, Akiko
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910049192902656
author Hamaguchi, Hiroki
Marumo, Naoki
Takeda, Akiko
author_facet Hamaguchi, Hiroki
Marumo, Naoki
Takeda, Akiko
contents Many practical optimization problems involve objective function values that are corrupted by unavoidable numerical errors. In smooth nonconvex optimization, quasi-Newton methods combined with line search are widely used due to their efficiency and scalability. These methods implicitly assume accurate function evaluations and thus may fail to converge in noisy settings. Developing fast and robust quasi-Newton methods for such scenarios is therefore crucial. To address this issue, we propose a noise-tolerant regularized quasi-Newton method equipped with a relaxed Armijo-type line search, designed to remain stable under inaccurate function evaluations. By combining a regularization parameter update rule inspired by Objective-Function-Free Optimization and the AdaGrad-Norm method, we establish a global convergence rate of $\mathcal{O}(1/\varepsilon^2)$ for reaching a first-order stationary point under the assumed error model. We performed extensive experiments on the CUTEst benchmark collection with artificially noisy objective function evaluations, as well as with low-precision floating-point arithmetic (64-, 32-, and 16-bit). The results demonstrate that the proposed method is substantially more robust than several existing methods, while maintaining competitive practical convergence speed and computational cost.
format Preprint
id arxiv_https___arxiv_org_abs_2603_10642
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Practical Regularized Quasi-Newton Methods with Inexact Function Values
Hamaguchi, Hiroki
Marumo, Naoki
Takeda, Akiko
Optimization and Control
90C53, 90C06, 65K05, 49M15
Many practical optimization problems involve objective function values that are corrupted by unavoidable numerical errors. In smooth nonconvex optimization, quasi-Newton methods combined with line search are widely used due to their efficiency and scalability. These methods implicitly assume accurate function evaluations and thus may fail to converge in noisy settings. Developing fast and robust quasi-Newton methods for such scenarios is therefore crucial. To address this issue, we propose a noise-tolerant regularized quasi-Newton method equipped with a relaxed Armijo-type line search, designed to remain stable under inaccurate function evaluations. By combining a regularization parameter update rule inspired by Objective-Function-Free Optimization and the AdaGrad-Norm method, we establish a global convergence rate of $\mathcal{O}(1/\varepsilon^2)$ for reaching a first-order stationary point under the assumed error model. We performed extensive experiments on the CUTEst benchmark collection with artificially noisy objective function evaluations, as well as with low-precision floating-point arithmetic (64-, 32-, and 16-bit). The results demonstrate that the proposed method is substantially more robust than several existing methods, while maintaining competitive practical convergence speed and computational cost.
title Practical Regularized Quasi-Newton Methods with Inexact Function Values
topic Optimization and Control
90C53, 90C06, 65K05, 49M15
url https://arxiv.org/abs/2603.10642