arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1507.07595math.OCcs.LGstat.ML
收藏

分布式随机方差约化梯度法及通信复杂度的下界

Distributed Stochastic Variance Reduced Gradient Methods and A Lower Bound for Communication Complexity

UC Berkeley(加州大学伯克利分校);The University of Iowa(爱荷华大学);Princeton University(普林斯顿大学)

Jason D. Lee, Qihang Lin, Tengyu Ma, Tianbao Yang

摘要:

研究了最小化凸函数平均值的分布式优化算法。这些应用包括统计机器学习中的经验风险最小化问题,其中数据集很大,必须存储在不同的机器上。我们设计了一个分布式的随机方差约简梯度算法,在一定的条件下的条件数,同时实现了最佳的并行运行时间,通信量和通信轮之间的所有分布式一阶方法常数的因素。我们的方法和它的加速扩展也优于现有的分布式算法的轮通信,只要条件数是不是太大的数据在每台机器的大小相比。我们还证明了一个下界的通信轮数广泛的一类分布式一阶方法,包括本文提出的算法。我们表明,我们的加速分布式随机方差降低梯度算法达到这个下界,使它使用最少的通信轮之间的所有分布式一阶算法。

英文摘要:

We study distributed optimization algorithms for minimizing the average of convex functions. The applications include empirical risk minimization problems in statistical machine learning where the datasets are large and have to be stored on different machines. We design a distributed stochastic variance reduced gradient algorithm that, under certain conditions on the condition number, simultaneously achieves the optimal parallel runtime, amount of communication and rounds of communication among all distributed first-order methods up to constant factors. Our method and its accelerated extension also outperform existing distributed algorithms in terms of the rounds of communication as long as the condition number is not too large compared to the size of data in each machine. We also prove a lower bound for the number of rounds of communication for a broad class of distributed first-order methods including the proposed algorithms in this paper. We show that our accelerated distributed stochastic variance reduced gradient algorithm achieves this lower bound so that it uses the fewest rounds of communication among all distributed first-order algorithms.

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。

↑