- Published 2013 in ArXiv

We study the performance of a family of randomized parallel coordinate descent methods for minimizing the sum of a nonsmooth and separable convex functions. The problem class includes as a special case L1-regularized L1 regression and the minimization of the exponential loss (“AdaBoost problem”). We assume the input data defining the loss function is contained in a sparse m× n matrix A with at most ω nonzeros in each row. Our methods need O(nβ/τ) iterations to find an approximate solution with high probability, where τ is the number of processors and β = 1 + (ω − 1)(τ − 1)/(n − 1) for the fastest variant. The notation hides dependence on quantities such as the required accuracy and confidence levels and the distance of the starting iterate from an optimal point. Since β/τ is a decreasing function of τ , the method needs fewer iterations when more processors are used. Certain variants of our algorithms perform on average only O(nnz(A)/n) arithmetic operations during a single iteration per processor and, because β decreases when ω does, fewer iterations are needed for sparser problems.

Citations per Year

Semantic Scholar estimates that this publication has **187** citations based on the available data.

See our **FAQ** for additional information.

Showing 1-10 of 103 extracted citations

Highly Influenced

10 Excerpts

Highly Influenced

6 Excerpts

Highly Influenced

20 Excerpts

Highly Influenced

6 Excerpts

Highly Influenced

7 Excerpts

Highly Influenced

7 Excerpts

Highly Influenced

6 Excerpts

Highly Influenced

10 Excerpts

Highly Influenced

4 Excerpts

Highly Influenced

9 Excerpts

@article{Fercoq2013SmoothMO,
title={Smooth minimization of nonsmooth functions with parallel coordinate descent methods},
author={Olivier Fercoq and Peter Richt{\'a}rik},
journal={CoRR},
year={2013},
volume={abs/1309.5885}
}