Linear convergence of Gearhart-Koshy accelerated Kaczmarz methods for tensor linear systems

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wang, Yijie, Sun, Yonghan, Han, Deren, Xie, Jiaxin
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910108898820096
author Wang, Yijie
Sun, Yonghan
Han, Deren
Xie, Jiaxin
author_facet Wang, Yijie
Sun, Yonghan
Han, Deren
Xie, Jiaxin
contents The generalized Gearhart-Koshy acceleration is a recent exact affine search technique designed for the method of cyclic projections onto hyperplanes, i.e., the Kaczmarz method. However, its convergence properties, particularly the linear convergence rate, have not been thoroughly established. In this paper, we systematically establish the linear convergence of the generalized Gearhart-Koshy accelerated Kaczmarz method for tensor linear systems, proving that it converges linearly to the unique least-norm solution. Our analysis is general and applies to several popular Kaczmarz variants, including incremental, shuffle-once, and random-reshuffling schemes, and demonstrates that this acceleration approach yields a better convergence upper bound compared to the plain Kaczmarz method. We also propose an efficient Gram-Schmidt-based implementation that computes the next iterate in linear time. Building on this implementation, we establish a connection between this acceleration framework and Arnoldi-type Krylov subspace methods, further highlighting its efficiency and potential. Our theoretical results are supported by numerical experiments.
format Preprint
id arxiv_https___arxiv_org_abs_2604_05816
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Linear convergence of Gearhart-Koshy accelerated Kaczmarz methods for tensor linear systems
Wang, Yijie
Sun, Yonghan
Han, Deren
Xie, Jiaxin
Numerical Analysis
The generalized Gearhart-Koshy acceleration is a recent exact affine search technique designed for the method of cyclic projections onto hyperplanes, i.e., the Kaczmarz method. However, its convergence properties, particularly the linear convergence rate, have not been thoroughly established. In this paper, we systematically establish the linear convergence of the generalized Gearhart-Koshy accelerated Kaczmarz method for tensor linear systems, proving that it converges linearly to the unique least-norm solution. Our analysis is general and applies to several popular Kaczmarz variants, including incremental, shuffle-once, and random-reshuffling schemes, and demonstrates that this acceleration approach yields a better convergence upper bound compared to the plain Kaczmarz method. We also propose an efficient Gram-Schmidt-based implementation that computes the next iterate in linear time. Building on this implementation, we establish a connection between this acceleration framework and Arnoldi-type Krylov subspace methods, further highlighting its efficiency and potential. Our theoretical results are supported by numerical experiments.
title Linear convergence of Gearhart-Koshy accelerated Kaczmarz methods for tensor linear systems
topic Numerical Analysis
url https://arxiv.org/abs/2604.05816