arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1506.04093stat.MLcs.LG
收藏

可分离鞍点问题的自适应随机原对偶坐标下降法

Adaptive Stochastic Primal-Dual Coordinate Descent for Separable Saddle Point Problems

The University of Edinburgh(爱丁堡大学)

Zhanxing Zhu, Amos J. Storkey

摘要:

考虑一类具有可分结构的一般凸凹鞍点问题,这种形式涵盖了广泛的机器学习应用。在这种问题结构下,我们遵循鞍点问题的原始-对偶更新框架,并将具有自适应步长的随机块坐标下降纳入该框架中。我们从理论上表明,我们的建议的自适应步长可能实现一个尖锐的线性收敛速度相比,现有的方法。此外,由于我们可以选择“小批量”块坐标更新,我们的方法也适合于大规模数据的并行处理。我们将所提出的方法应用于正则化经验风险最小化,并表明它在合成数据集和真实数据集上的表现往往优于最先进的方法。

英文摘要:

We consider a generic convex-concave saddle point problem with separable structure, a form that covers a wide-ranged machine learning applications. Under this problem structure, we follow the framework of primal-dual updates for saddle point problems, and incorporate stochastic block coordinate descent with adaptive stepsize into this framework. We theoretically show that our proposal of adaptive stepsize potentially achieves a sharper linear convergence rate compared with the existing methods. Additionally, since we can select "mini-batch" of block coordinates to update, our method is also amenable to parallel processing for large-scale data. We apply the proposed method to regularized empirical risk minimization and show that it performs comparably or, more often, better than state-of-the-art methods on both synthetic and real-world data sets.

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。

↑