# Rows versus Columns: Randomized Kaczmarz or Gauss-Seidel for Ridge Regression

@article{Hefny2017RowsVC,
title={Rows versus Columns: Randomized Kaczmarz or Gauss-Seidel for Ridge Regression},
author={Ahmed Hefny and Deanna Needell and Aaditya Ramdas},
journal={SIAM J. Scientific Computing},
year={2017},
volume={39}
}
• Published 2017
• Mathematics, Computer Science
• SIAM J. Scientific Computing
• The Kaczmarz and Gauss-Seidel methods aim to solve a linear $m \times n$ system $\boldsymbol{X} \boldsymbol{\beta} = \boldsymbol{y}$ by iteratively refining the solution estimate; the former uses random rows of $\boldsymbol{X}$ {to update $\boldsymbol{\beta}$ given the corresponding equations} and the latter uses random columns of $\boldsymbol{X}$ {to update corresponding coordinates in $\boldsymbol{\beta}$}. Interest in these methods was recently revitalized by a proof of Strohmer and… CONTINUE READING

#### Citations

##### Publications citing this paper.
SHOWING 1-10 OF 18 CITATIONS

## Variant of greedy randomized Kaczmarz for ridge regression

• Mathematics
• 2019

## A Doubly Stochastic Gauss-Seidel Algorithm for Solving Linear Equations and Certain Convex Minimization Problems

• Mathematics
• 2018
VIEW 2 EXCERPTS
CITES METHODS

## CONVERGENCE OF THE RANDOMIZED BLOCK GAUSS-SEIDEL METHOD

• WU WEIMAGGIE
• 2018

## A linearly convergent doubly stochastic Gauss–Seidel algorithm for solving linear equations and a certain class of over-parameterized optimization problems

• Computer Science, Mathematics
• Math. Program.
• 2019
VIEW 2 EXCERPTS
CITES METHODS

## Greedy Block Gauss-Seidel Methods for Solving Large Linear Least Squares Problem

• Mathematics, Computer Science
• ArXiv
• 2020
VIEW 1 EXCERPT
CITES METHODS

## On Generalization and Acceleration of Randomized Projection Methods for Linear Feasibility Problems

• Mathematics
• 2020

## Pseudoinverse-free randomized extended block Kaczmarz for solving least squares

• ArXiv
• 2020
VIEW 1 EXCERPT
CITES BACKGROUND

## A novel greedy Gauss-Seidel method for solving large linear least squares problem

• Mathematics, Computer Science
• ArXiv
• 2020
VIEW 2 EXCERPTS

## Computational and Statistical Advances in Testing and Learning

VIEW 1 EXCERPT
CITES BACKGROUND

## Tight upper bounds for the convergence of the randomized extended Kaczmarz and Gauss-Seidel algorithms

• Kui Du
• Computer Science, Mathematics
• Numer. Linear Algebra Appl.
• 2019
VIEW 1 EXCERPT

#### References

##### Publications referenced by this paper.
SHOWING 1-10 OF 35 REFERENCES

## Convergence Properties of the Randomized Extended Gauss-Seidel and Kaczmarz Methods

• Computer Science, Mathematics
• SIAM J. Matrix Anal. Appl.
• 2015
VIEW 6 EXCERPTS

## Iteration complexity of randomized block-coordinate descent methods for minimizing a composite function

• Mathematics, Computer Science
• Math. Program.
• 2014
VIEW 1 EXCERPT

## Almost Sure Convergence of the Kaczmarz Algorithm with Random Measurements

• Mathematics
• 2012
VIEW 1 EXCERPT

## Coordinate Descent Face-Off: Primal or Dual?

• Mathematics
• 2016
VIEW 1 EXCERPT

## Acceleration of randomized Kaczmarz method via the Johnson–Lindenstrauss Lemma

• Mathematics, Computer Science
• Numerical Algorithms
• 2011

## Paved with Good Intentions: Analysis of a Randomized Block Kaczmarz Method

• Computer Science, Mathematics
• ArXiv
• 2014
VIEW 1 EXCERPT

## A Randomized Kaczmarz Algorithm with Exponential Convergence

• Mathematics
• 2007

## Elementary Estimators for High-Dimensional Linear Regression

• Computer Science
• ICML
• 2014
VIEW 2 EXCERPTS

## Ridge Regression Learning Algorithm in Dual Variables

• Computer Science
• ICML
• 1998

## Kaczmarz Algorithm For Tikhonov Regularization Problem ∗

VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL