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 1303.2289math.OCcs.DCcs.SYeess.SY
收藏

时变有向图上的分布式优化

Distributed optimization over time-varying directed graphs

University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)

Angelia Nedic, Alex Olshevsky

AI总结:

针对时变有向通信图上的分布式优化问题,提出基于广播的次梯度推送算法,在次梯度有界假设下实现所有节点收敛到最优值,收敛率为O(ln(t)/√t)。

摘要:

我们考虑由一组节点进行的分布式优化,每个节点可以访问自己的凸函数,其集体目标是使函数之和最小化。节点之间的通信由时变有向图序列描述,该序列是一致强连通的。对于这种通信,假设每个节点知道其出度,我们开发了一种基于广播的算法,称为次梯度推送,该算法在次梯度有界的标准假设下将每个节点引导至最优值。次梯度推送在实现时不需要知道代理数量或图序列。我们的分析表明,次梯度推送算法以$O(\ln(t)/\sqrt{t})$的速率收敛,其中常数取决于节点的初始值、次梯度范数,更有趣的是,还取决于共识速度和节点间影响力不平衡程度。

英文摘要:

We consider distributed optimization by a collection of nodes, each having access to its own convex function, whose collective goal is to minimize the sum of the functions. The communications between nodes are described by a time-varying sequence of directed graphs, which is uniformly strongly connected. For such communications, assuming that every node knows its out-degree, we develop a broadcast-based algorithm, termed the subgradient-push, which steers every node to an optimal value under a standard assumption of subgradient boundedness. The subgradient-push requires no knowledge of either the number of agents or the graph sequence to implement. Our analysis shows that the subgradient-push algorithm converges at a rate of $O(\ln(t)/\sqrt{t})$, where the constant depends on the initial values at the nodes, the subgradient norms, and, more interestingly, on both the consensus speed and the imbalances of influence among the nodes.

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。

↑