Stochastic Dual Coordinate Ascent with Adaptive Probabilities
Abstract
This paper introduces AdaSDCA: an adaptive variant of stochastic dual coordinate ascent (SDCA) for solving the regularized empirical risk minimization problems. Our modification consists in allowing the method adaptively change the probability distribution over the dual variables throughout the iterative process. AdaSDCA achieves provably better complexity bound than SDCA with the best fixed probability distribution, known as importance sampling. However, it is of a theoretical character as it is expensive to implement. We also propose AdaSDCA+: a practical variant which in our experiments outperforms existing non-adaptive methods.
Cite
Text
Csiba et al. "Stochastic Dual Coordinate Ascent with Adaptive Probabilities." International Conference on Machine Learning, 2015.Markdown
[Csiba et al. "Stochastic Dual Coordinate Ascent with Adaptive Probabilities." International Conference on Machine Learning, 2015.](https://mlanthology.org/icml/2015/csiba2015icml-stochastic/)BibTeX
@inproceedings{csiba2015icml-stochastic,
title = {{Stochastic Dual Coordinate Ascent with Adaptive Probabilities}},
author = {Csiba, Dominik and Qu, Zheng and Richtarik, Peter},
booktitle = {International Conference on Machine Learning},
year = {2015},
pages = {674-683},
volume = {37},
url = {https://mlanthology.org/icml/2015/csiba2015icml-stochastic/}
}