arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1702.07367math.NAcs.NAstat.ML
收藏

大型线性最小二乘问题的随机牛顿法和拟牛顿法

Stochastic Newton and Quasi-Newton Methods for Large Linear Least-squares Problems

Julianne Chung, Matthias Chung, J. Tanner Slagel, Luis Tenorio

摘要:

我们描述了随机牛顿和随机拟牛顿方法,以有效地解决大型线性最小二乘问题,其中非常大的数据集带来了显着的计算负担(例如,该大小可能超过计算机存储器或实时收集数据)。在我们提出的框架中,在两个不同的框架中引入了随机性作为克服这些计算限制的手段,并考虑了可以利用结构和/或稀疏性的概率分布。给出了随机牛顿法和随机拟牛顿法近似一致性的理论结果。结果表明,特别是,随机牛顿迭代,与随机拟牛顿迭代,可能不会收敛到所需的最小二乘解。数值例子,包括极端学习机的例子,展示了这些方法的潜在应用。

英文摘要:

We describe stochastic Newton and stochastic quasi-Newton approaches to efficiently solve large linear least-squares problems where the very large data sets present a significant computational burden (e.g., the size may exceed computer memory or data are collected in real-time). In our proposed framework, stochasticity is introduced in two different frameworks as a means to overcome these computational limitations, and probability distributions that can exploit structure and/or sparsity are considered. Theoretical results on consistency of the approximations for both the stochastic Newton and the stochastic quasi-Newton methods are provided. The results show, in particular, that stochastic Newton iterates, in contrast to stochastic quasi-Newton iterates, may not converge to the desired least-squares solution. Numerical examples, including an example from extreme learning machines, demonstrate the potential applications of these 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。

↑