An Efficient Reversible Algorithm for Linear Regression
Erik D. Demaine, Jayson Lynch, Jiaying Sun

TL;DR
This paper introduces a reversible algorithm for linear regression that matches the efficiency of traditional methods, expanding reversible matrix operations to rectangular matrices and inversion.
Contribution
The paper develops a reversible algorithm for linear regression, including ridge regression, with optimal asymptotic complexity, extending reversible matrix multiplication and inversion techniques.
Findings
Reversible algorithm matches standard algorithms in time and space complexity.
Extended reversible matrix multiplication to rectangular matrices.
Achieved reversible matrix inversion with comparable efficiency.
Abstract
This paper presents an efficient reversible algorithm for linear regression, both with and without ridge regression. Our reversible algorithm matches the asymptotic time and space complexity of standard irreversible algorithms for this problem. Needed for this result is the expansion of the analysis of efficient reversible matrix multiplication to rectangular matrices and matrix inversion.
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
TopicsParallel Computing and Optimization Techniques · Quantum Computing Algorithms and Architecture · Matrix Theory and Algorithms
