arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1104.1157math.OCcs.SYeess.SY
收藏

加速对偶下降用于网络优化

Accelerated Dual Descent for Network Optimization

University of Pennsylvania(宾夕法尼亚大学);Massachusetts Institute of Technology(麻省理工学院)

M. Zargham, A. Ribeiro, A. Jadbabaie, A. Ozdaglar

AI总结:

本文提出一种使用近似牛顿方向加速对偶下降收敛的分布式算法,通过矩阵分裂和稀疏泰勒近似实现超线性收敛,数值实验表明收敛速度比现有方法快一到两个数量级。

摘要:

对偶下降方法常用于解决网络优化问题,因为其实现可以通过网络分布式进行。然而,它们的收敛速度通常非常慢。本文介绍了一系列使用近似牛顿方向来加速传统对偶下降收敛速度的对偶下降算法。这些近似方向可以通过局部信息交换计算,从而保留分布式实现的优点。近似牛顿方向通过矩阵分裂技术和逆Hessian的稀疏泰勒近似获得。我们表明,与传统牛顿方法类似,所提算法在最优值邻域内表现出超线性收敛。数值分析证实,收敛时间比现有分布式优化方法快一到两个数量级。还介绍了与最近使用共识迭代计算近似牛顿方向的发展的联系。

英文摘要:

Dual descent methods are commonly used to solve network optimization problems because their implementation can be distributed through the network. However, their convergence rates are typically very slow. This paper introduces a family of dual descent algorithms that use approximate Newton directions to accelerate the convergence rate of conventional dual descent. These approximate directions can be computed using local information exchanges thereby retaining the benefits of distributed implementations. The approximate Newton directions are obtained through matrix splitting techniques and sparse Taylor approximations of the inverse Hessian.We show that, similarly to conventional Newton methods, the proposed algorithm exhibits superlinear convergence within a neighborhood of the optimal value. Numerical analysis corroborates that convergence times are between one to two orders of magnitude faster than existing distributed optimization methods. A connection with recent developments that use consensus iterations to compute approximate Newton directions is also presented.

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。

↑