On the Complexity of Parallel Coordinate Descent
Optimization and Control
2015-03-11 v1
Abstract
In this work we study the parallel coordinate descent method (PCDM) proposed by Richt\'arik and Tak\'a\v{c} [26] for minimizing a regularized convex function. We adopt elements from the work of Xiao and Lu [39], and combine them with several new insights, to obtain sharper iteration complexity results for PCDM than those presented in [26]. Moreover, we show that PCDM is monotonic in expectation, which was not confirmed in [26], and we also derive the first high probability iteration complexity result where the initial levelset is unbounded.
Cite
@article{arxiv.1503.03033,
title = {On the Complexity of Parallel Coordinate Descent},
author = {Rachael Tappenden and Martin Takáč and Peter Richtárik},
journal= {arXiv preprint arXiv:1503.03033},
year = {2015}
}
Comments
26 pages; 2 figures