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 2207.06253stat.MEcs.DC
收藏

带修正量和M-估计量的通信有效分布式Newton类优化

Communication-efficient Distributed Newton-like Optimization with Gradients and M-estimators

Ziyan Yin

摘要:

在现代数据科学中,大规模数据在大量位置上存储和处理是很常见的。出于保密等原因,只有来自每个平行中心的有限数据信息才有资格被传输。为了更有效地解决这些问题,正在积极开发一组通信高效的方法。我们提出了两个通信效率的牛顿型算法,结合M-估计和从每个数据中心收集的梯度。它们是通过构建两个费舍尔信息估计全球与这些通信有效的统计。享受更高的收敛速度,这个框架改进了现有的牛顿类方法。此外,我们提出了两个偏差调整的一步分布估计。当中心样本量的平方大于中心总数时,它们与全局$M$估计量一样有效。我们的方法的优点是说明了广泛的理论和经验证据。

英文摘要:

In modern data science, it is common that large-scale data are stored and processed parallelly across a great number of locations. For reasons including confidentiality concerns, only limited data information from each parallel center is eligible to be transferred. To solve these problems more efficiently, a group of communication-efficient methods are being actively developed. We propose two communication-efficient Newton-type algorithms, combining the M-estimator and the gradient collected from each data center. They are created by constructing two Fisher information estimators globally with those communication-efficient statistics. Enjoying a higher rate of convergence, this framework improves upon existing Newton-like methods. Moreover, we present two bias-adjusted one-step distributed estimators. When the square of the center-wise sample size is of a greater magnitude than the total number of centers, they are as efficient as the global $M$-estimator asymptotically. The advantages of our methods are illustrated by extensive theoretical and empirical evidences.

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。

↑