Fast Algorithms for $\ell_p$-Regression
Abstract
The -norm regression problem is a classic problem in optimization with wide ranging applications in machine learning and theoretical computer science. The goal is to compute , where and . Efficient high-accuracy algorithms for the problem have been challenging both in theory and practice and the state of the art algorithms require linear system solves for . In this paper, we provide new algorithms for -regression (and a more general formulation of the problem) that obtain a high-accuracy solution in linear system solves. We further propose a new inverse maintenance procedure that speeds-up our algorithm to total runtime, where denotes the running time for multiplying matrices. Additionally, we give the first Iteratively Reweighted Least Squares (IRLS) algorithm that is guaranteed to converge to an optimum in a few iterations. Our IRLS algorithm has shown exceptional practical performance, beating the currently available implementations in MATLAB/CVX by 10-50x.
Cite
@article{arxiv.2211.03963,
title = {Fast Algorithms for $\ell_p$-Regression},
author = {Deeksha Adil and Rasmus Kyng and Richard Peng and Sushant Sachdeva},
journal= {arXiv preprint arXiv:2211.03963},
year = {2023}
}
Comments
This paper is a coherent algorithmic framework that combines and simplifies our previous works: 1. arXiv:1901.06764 2. arXiv:1907.07167 3. arXiv:1910.10571