arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1605.08795cs.DS
收藏

贪婪列子集选择:新的界和分布式算法

Greedy Column Subset Selection: New Bounds and Distributed Algorithms

Jason Altschuler, Aditya Bhaskara, Gang Fu, Vahab Mirrokni, Afshin Rostamizadeh, Morteza Zadimoghaddam

摘要:

列子集选择问题最近吸引了大量的研究,其中特征选择是一个明显而重要的应用。在已被应用于解决这个问题的技术中,贪心算法已被证明是相当有效的。然而,其性能的理论保证还没有被彻底探讨,特别是在分布式环境中。在本文中,我们研究了贪心算法的列子集选择问题从理论和实证的角度来看,并显示其有效性在分布式设置。特别是,我们提供了一个改进的近似保证的贪心算法,我们表明是紧到一个常数的因素,并提出了第一个分布式实现可证明的近似因子。我们使用的想法随机组合的核心集,最近开发的子模块最大化的背景下。最后,通过实验验证了该分布式算法的有效性.

英文摘要:

The problem of column subset selection has recently attracted a large body of research, with feature selection serving as one obvious and important application. Among the techniques that have been applied to solve this problem, the greedy algorithm has been shown to be quite effective in practice. However, theoretical guarantees on its performance have not been explored thoroughly, especially in a distributed setting. In this paper, we study the greedy algorithm for the column subset selection problem from a theoretical and empirical perspective and show its effectiveness in a distributed setting. In particular, we provide an improved approximation guarantee for the greedy algorithm which we show is tight up to a constant factor, and present the first distributed implementation with provable approximation factors. We use the idea of randomized composable core-sets, developed recently in the context of submodular maximization. Finally, we validate the effectiveness of this distributed algorithm via an empirical study.

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。

↑