DMCA
Stochastic dual coordinate ascent with adaptive probabilities. ICML 2015. [2] Shai Shalev-Shwartz and Tong Zhang. Stochastic dual coordinate ascent methods for regularized loss
| Citations: | 3 - 2 self |
BibTeX
@MISC{Csiba_stochasticdual,
author = {Dominik Csiba and Zheng Qu},
title = {Stochastic dual coordinate ascent with adaptive probabilities. ICML 2015. [2] Shai Shalev-Shwartz and Tong Zhang. Stochastic dual coordinate ascent methods for regularized loss},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
This paper introduces AdaSDCA: an adap-tive variant of stochastic dual coordinate as-cent (SDCA) for solving the regularized empir-ical risk minimization problems. Our modifica-tion consists in allowing the method adaptively change the probability distribution over the dual variables throughout the iterative process. AdaS-DCA achieves provably better complexity bound than SDCA with the best fixed probability dis-tribution, known as importance sampling. How-ever, it is of a theoretical character as it is expen-sive to implement. We also propose AdaSDCA+: a practical variant which in our experiments out-performs existing non-adaptive methods. 1.
