arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1312.7853cs.LGmath.OCstat.ML
收藏

基于近似牛顿型方法的通信效率分布式优化

Communication Efficient Distributed Optimization using an Approximate Newton-type Method

Toyota Technological Institute(丰田工业大学);Technion(以色列理工学院);Rutgers University(罗格斯大学);Baidu(百度)

Ohad Shamir, Nathan Srebro, Tong Zhang

摘要:

我们提出了一种新的牛顿型方法的分布式优化,这是特别适合于随机优化和学习问题。对于二次型目标,该方法具有线性收敛速度,可证明\emph{improves}与数据大小,在合理的假设下,需要一个基本上恒定的迭代次数。我们提供了理论和经验证据的优势,我们的方法相比,其他方法,如单次参数平均和ADMM。

英文摘要:

We present a novel Newton-type method for distributed optimization, which is particularly well suited for stochastic optimization and learning problems. For quadratic objectives, the method enjoys a linear rate of convergence which provably \emph{improves} with the data size, requiring an essentially constant number of iterations under reasonable assumptions. We provide theoretical and empirical evidence of the advantages of our method compared to other approaches, such as one-shot parameter averaging and ADMM.

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。

↑