Inexact Limited Memory Bundle Method

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Lampainen, Jenni, Joki, Kaisa, Karmitsa, Napsu, Mäkelä, Marko M.
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914461395189760
author Lampainen, Jenni
Joki, Kaisa
Karmitsa, Napsu
Mäkelä, Marko M.
author_facet Lampainen, Jenni
Joki, Kaisa
Karmitsa, Napsu
Mäkelä, Marko M.
contents Large-scale nonsmooth optimization problems arise in many real-world applications, but obtaining exact function and subgradient values for these problems may be computationally expensive or even infeasible. In many practical settings, only inexact information is available due to measurement or modeling errors, privacy-preserving computations, or stochastic approximations, making inexact optimization methods particularly relevant. In this paper, we propose a novel inexact limited memory bundle method for large-scale nonsmooth nonconvex optimization. The method tolerates noise in both function values and subgradients. We prove the global convergence of the proposed method to an approximate stationary point. Numerical experiments with different levels of noise in function and/or subgradient values show that the method performs well with both exact and noisy data. In particular, the results demonstrate competitiveness in large-scale nonsmooth optimization and highlight the suitability of the method for applications where noise is unavoidable, such as differential privacy in machine learning.
format Preprint
id arxiv_https___arxiv_org_abs_2604_08067
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Inexact Limited Memory Bundle Method
Lampainen, Jenni
Joki, Kaisa
Karmitsa, Napsu
Mäkelä, Marko M.
Optimization and Control
90C26, 90C06, 49J52, 65K05
Large-scale nonsmooth optimization problems arise in many real-world applications, but obtaining exact function and subgradient values for these problems may be computationally expensive or even infeasible. In many practical settings, only inexact information is available due to measurement or modeling errors, privacy-preserving computations, or stochastic approximations, making inexact optimization methods particularly relevant. In this paper, we propose a novel inexact limited memory bundle method for large-scale nonsmooth nonconvex optimization. The method tolerates noise in both function values and subgradients. We prove the global convergence of the proposed method to an approximate stationary point. Numerical experiments with different levels of noise in function and/or subgradient values show that the method performs well with both exact and noisy data. In particular, the results demonstrate competitiveness in large-scale nonsmooth optimization and highlight the suitability of the method for applications where noise is unavoidable, such as differential privacy in machine learning.
title Inexact Limited Memory Bundle Method
topic Optimization and Control
90C26, 90C06, 49J52, 65K05
url https://arxiv.org/abs/2604.08067