Fast Distributed Coordinate Descent for Non-Strongly Convex Losses

Olivier Fercoq, Zheng Qu, Peter Richtárik, Martin Takác

Abstract

We propose an efficient distributed randomized coordinate descent method for minimizing regularized non-strongly convex loss functions. The method attains the optimal $O(1/k^2)$ convergence rate, where $k$ is the iteration counter. The core of the work is the theoretical study of stepsize parameters. We have implemented the method on Archer - the largest supercomputer in the UK - and show that the method is capable of solving a (synthetic) LASSO optimization problem with 50 billion variables.
BibTeX
@inproceedings{fercoq2014fast,
  author = {Olivier Fercoq and Zheng Qu and Peter Richtárik and Martin Takác},
  title = {{Fast Distributed Coordinate Descent for Non-Strongly Convex Losses}},
  booktitle = {MLSP},
  year = {2014},
  url = {https://openreview.net/forum?id=RZ-jzoKf_GC},
}

Loading related content...

Figure