An Asynchronous Parallel Randomized Kaczmarz Algorithm
Ji Liu, Stephen J. Wright, Srikrishna Sridhar
TL;DR
This paper introduces an asynchronous parallel version of the randomized Kaczmarz algorithm for solving linear systems, demonstrating linear convergence and near-linear speedup with multiple processors.
Contribution
It presents a novel asynchronous parallel algorithm for RK, with theoretical analysis showing convergence and efficiency gains over traditional methods.
Findings
Linear convergence of the asynchronous algorithm
Near-linear speedup with multiple processors
Bounded speedup related to number of matrix rows
Abstract
We describe an asynchronous parallel variant of the randomized Kaczmarz (RK) algorithm for solving the linear system . The analysis shows linear convergence and indicates that nearly linear speedup can be expected if the number of processors is bounded by a multiple of the number of rows in .
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.
Taxonomy
TopicsStochastic Gradient Optimization Techniques · Complexity and Algorithms in Graphs · Sparse and Compressive Sensing Techniques