Incremental Gauss--Newton Methods with Superlinear Convergence Rates

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhou, Zhiling, Liu, Zhuanghua, Liu, Chengchang, Luo, Luo
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929408544079872
author Zhou, Zhiling
Liu, Zhuanghua
Liu, Chengchang
Luo, Luo
author_facet Zhou, Zhiling
Liu, Zhuanghua
Liu, Chengchang
Luo, Luo
contents This paper addresses the challenge of solving large-scale nonlinear equations with Hölder continuous Jacobians. We introduce a novel Incremental Gauss--Newton (IGN) method within explicit superlinear convergence rate, which outperforms existing methods that only achieve linear convergence rate. In particular, we formulate our problem by the nonlinear least squares with finite-sum structure, and our method incrementally iterates with the information of one component in each round. We also provide a mini-batch extension to our IGN method that obtains an even faster superlinear convergence rate. Furthermore, we conduct numerical experiments to show the advantages of the proposed methods.
format Preprint
id arxiv_https___arxiv_org_abs_2407_03195
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Incremental Gauss--Newton Methods with Superlinear Convergence Rates
Zhou, Zhiling
Liu, Zhuanghua
Liu, Chengchang
Luo, Luo
Optimization and Control
Machine Learning
This paper addresses the challenge of solving large-scale nonlinear equations with Hölder continuous Jacobians. We introduce a novel Incremental Gauss--Newton (IGN) method within explicit superlinear convergence rate, which outperforms existing methods that only achieve linear convergence rate. In particular, we formulate our problem by the nonlinear least squares with finite-sum structure, and our method incrementally iterates with the information of one component in each round. We also provide a mini-batch extension to our IGN method that obtains an even faster superlinear convergence rate. Furthermore, we conduct numerical experiments to show the advantages of the proposed methods.
title Incremental Gauss--Newton Methods with Superlinear Convergence Rates
topic Optimization and Control
Machine Learning
url https://arxiv.org/abs/2407.03195