Accelerated proximal stochastic dual coordinate ascent for regularized loss minimization
Accelerated proximal stochastic dual coordinate ascent for regularized loss minimization
复制标题
DOI：
10.1007/s10107-014-0839-0
复制
发表时间：
2013-09
影响因子：
2.7
通讯作者：
Shai Shalev-Shwartz;Tong Zhang
中科院分区：
文献类型：
--
作者：
Shai Shalev-Shwartz;Tong Zhang
我们介绍了一个近端版本的随机对偶坐标上升法，并展示了如何使用内外迭代过程来加速该方法。我们分析了框架的运行时间，并获得了改善各种关键机器学习优化问题的最新结果的比率，包括SVM，逻辑回归，岭回归，Lasso和多类SVM。实验验证了我们的理论发现。
We introduce a proximal version of the stochastic dual coordinate ascent method and show how to accelerate the method using an inner-outer iteration procedure. We analyze the runtime of the framework and obtain rates that improve state-of-the-art results for various key machine learning optimization problems including SVM, logistic regression, ridge regression, Lasso, and multiclass SVM. Experiments validate our theoretical findings.