On the exponential convergence of the Kaczmarz algorithm
Liang Dai, Thomas Sch\"on

TL;DR
This paper establishes a new exponential convergence rate for the Kaczmarz algorithm by interpreting its solution path as a dynamical system and applying stability analysis.
Contribution
It introduces a novel dynamical system perspective to analyze the Kaczmarz algorithm, leading to improved convergence bounds.
Findings
Proves exponential convergence of the Kaczmarz algorithm.
Derives a new bound on the convergence rate.
Compares the new bound with existing bounds.
Abstract
The Kaczmarz algorithm (KA) is a popular method for solving a system of linear equations. In this note we derive a new exponential convergence result for the KA. The key allowing us to establish the new result is to rewrite the KA in such a way that its solution path can be interpreted as the output from a particular dynamical system. The asymptotic stability results of the corresponding dynamical system can then be leveraged to prove exponential convergence of the KA. The new bound is also compared to existing bounds.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
