Approaching Optimality for Solving Dense Linear Systems with Low-Rank Structure

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Dereziński, Michał, Sidford, Aaron
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908451551051776
author Dereziński, Michał
Sidford, Aaron
author_facet Dereziński, Michał
Sidford, Aaron
contents We provide new high-accuracy randomized algorithms for solving linear systems and regression problems that are well-conditioned except for $k$ large singular values. For solving such $d \times d$ positive definite system our algorithms succeed whp. and run in time $\tilde O(d^2 + k^ω)$. For solving such regression problems in a matrix $\mathbf{A} \in \mathbb{R}^{n \times d}$ our methods succeed whp. and run in time $\tilde O(\mathrm{nnz}(\mathbf{A}) + d^2 + k^ω)$ where $ω$ is the matrix multiplication exponent and $\mathrm{nnz}(\mathbf{A})$ is the number of non-zeros in $\mathbf{A}$. Our methods nearly-match a natural complexity limit under dense inputs for these problems and improve upon a trade-off in prior approaches that obtain running times of either $\tilde O(d^{2.065}+k^ω)$ or $\tilde O(d^2 + dk^{ω-1})$ for $d\times d$ systems. Moreover, we show how to obtain these running times even under the weaker assumption that all but $k$ of the singular values have a suitably bounded generalized mean. Consequently, we give the first nearly-linear time algorithm for computing a multiplicative approximation to the nuclear norm of an arbitrary dense matrix. Our algorithms are built on three general recursive preconditioning frameworks, where matrix sketching and low-rank update formulas are carefully tailored to the problems' structure.
format Preprint
id arxiv_https___arxiv_org_abs_2507_11724
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Approaching Optimality for Solving Dense Linear Systems with Low-Rank Structure
Dereziński, Michał
Sidford, Aaron
Data Structures and Algorithms
Numerical Analysis
Optimization and Control
Machine Learning
We provide new high-accuracy randomized algorithms for solving linear systems and regression problems that are well-conditioned except for $k$ large singular values. For solving such $d \times d$ positive definite system our algorithms succeed whp. and run in time $\tilde O(d^2 + k^ω)$. For solving such regression problems in a matrix $\mathbf{A} \in \mathbb{R}^{n \times d}$ our methods succeed whp. and run in time $\tilde O(\mathrm{nnz}(\mathbf{A}) + d^2 + k^ω)$ where $ω$ is the matrix multiplication exponent and $\mathrm{nnz}(\mathbf{A})$ is the number of non-zeros in $\mathbf{A}$. Our methods nearly-match a natural complexity limit under dense inputs for these problems and improve upon a trade-off in prior approaches that obtain running times of either $\tilde O(d^{2.065}+k^ω)$ or $\tilde O(d^2 + dk^{ω-1})$ for $d\times d$ systems. Moreover, we show how to obtain these running times even under the weaker assumption that all but $k$ of the singular values have a suitably bounded generalized mean. Consequently, we give the first nearly-linear time algorithm for computing a multiplicative approximation to the nuclear norm of an arbitrary dense matrix. Our algorithms are built on three general recursive preconditioning frameworks, where matrix sketching and low-rank update formulas are carefully tailored to the problems' structure.
title Approaching Optimality for Solving Dense Linear Systems with Low-Rank Structure
topic Data Structures and Algorithms
Numerical Analysis
Optimization and Control
Machine Learning
url https://arxiv.org/abs/2507.11724