Proximal Stochastic Dual Coordinate Ascent
Machine Learning
2012-11-13 v1 Machine Learning
Optimization and Control
Abstract
We introduce a proximal version of dual coordinate ascent method. We demonstrate how the derived algorithmic framework can be used for numerous regularized loss minimization problems, including regularization and structured output SVM. The convergence rates we obtain match, and sometimes improve, state-of-the-art results.
Cite
@article{arxiv.1211.2717,
title = {Proximal Stochastic Dual Coordinate Ascent},
author = {Shai Shalev-Shwartz and Tong Zhang},
journal= {arXiv preprint arXiv:1211.2717},
year = {2012}
}