arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1603.02412math.OCcs.LGstat.ML
收藏

正则化经验风险最小化问题的随机对偶平均方法

Stochastic dual averaging methods using variance reduction techniques for regularized empirical risk minimization problems

Tokyo Institute of Technology(东京工业大学);Japan Science and Technology Agency(日本科学技术振兴机构)

Tomoya Murata, Taiji Suzuki

摘要:

我们考虑一个复合凸最小化问题与正则化的经验风险最小化,这经常出现在机器学习。本文提出了两种新的随机梯度法,它们是基于方差缩减的随机对偶平均方法。我们的方法生成一个稀疏的解决方案比现有的方法,因为我们不需要采取的平均历史的解决方案。这在可解释性和概括性方面都是有利的。此外,我们的方法有理论支持的强和非强凸正则化,并实现现有的非加速随机梯度法之间的最佳收敛速度。

英文摘要:

We consider a composite convex minimization problem associated with regularized empirical risk minimization, which often arises in machine learning. We propose two new stochastic gradient methods that are based on stochastic dual averaging method with variance reduction. Our methods generate a sparser solution than the existing methods because we do not need to take the average of the history of the solutions. This is favorable in terms of both interpretability and generalization. Moreover, our methods have theoretical support for both a strongly and a non-strongly convex regularizer and achieve the best known convergence rates among existing nonaccelerated stochastic gradient methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑