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 2006.01665math.OC
收藏

多重一致梯度步长嵌套分散梯度法的收敛性

On the Convergence of Nested Decentralized Gradient Methods with Multiple Consensus and Gradient Steps

Albert S. Berahas, Raghu Bollapragada, Ermin Wei

摘要:

在本文中,我们考虑最小化的局部凸目标函数在分布式设置,通信和/或计算的成本可能是昂贵的总和。我们扩展和推广了对一类嵌套的基于梯度的分布式算法(NEAR-DGD; Berahas,Bollapragada,Keskar和Wei,2018)的分析,以解释每次迭代时的多个梯度步骤。我们执行多个梯度步骤上的收敛速度收敛速率和收敛的邻域的大小的影响,并证明R-线性收敛的精确解与一个固定的梯度步骤和越来越多的共识步骤。我们测试的性能的广义方法上的二次函数和显示的效果,多个共识和梯度步骤的迭代次数,梯度评估,通信数量和成本。

英文摘要:

In this paper, we consider minimizing a sum of local convex objective functions in a distributed setting, where the cost of communication and/or computation can be expensive. We extend and generalize the analysis for a class of nested gradient-based distributed algorithms (NEAR-DGD; Berahas, Bollapragada, Keskar and Wei, 2018) to account for multiple gradient steps at every iteration. We show the effect of performing multiple gradient steps on the rate of convergence and on the size of the neighborhood of convergence, and prove R-Linear convergence to the exact solution with a fixed number of gradient steps and increasing number of consensus steps. We test the performance of the generalized method on quadratic functions and show the effect of multiple consensus and gradient steps in terms of iterations, number of gradient evaluations, number of communications and cost.

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。

↑