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 1211.2132math.OCcs.DCcs.SYeess.SY
收藏

网络化优化的加速梯度方法

Accelerated Gradient Methods for Networked Optimization

ACCESS Linnaeus Center, Electrical Engineering, Royal Institute of Technology(皇家理工学院电气工程学院林奈中心);Department of Electrical and Electronic Engineering, The University of Melbourne(墨尔本大学电气与电子工程系)

Euhanna Ghadimi, Iman Shames, Mikael Johansson

AI总结:

针对具有Lipschitz连续梯度的强凸函数的网络约束优化问题,提出多步梯度方法,通过确定最优算法参数实现最快收敛,并量化不确定性影响,在资源分配、分布式平均和互联网拥塞控制中验证了优于标准梯度法的加速效果。

摘要:

我们开发了用于网络约束优化的多步梯度方法,适用于具有Lipschitz连续梯度的强凸函数。给定底层网络的拓扑结构和目标函数Hessian的界限,我们确定了保证最快收敛的算法参数,并描述了在哪些情况下可以获得相对于标准梯度方法的显著加速。此外,我们量化了梯度方法及其加速版本在问题数据不确定性下的性能影响,并得出结论:在大多数情况下,我们提出的方法优于梯度下降。最后,我们将所提出的技术应用于三个工程问题:网络范围预算约束下的资源分配、分布式平均和互联网拥塞控制。在所有情况下,我们证明我们的算法比文献中报道的替代算法收敛更快。

英文摘要:

We develop multi-step gradient methods for network-constrained optimization of strongly convex functions with Lipschitz-continuous gradients. Given the topology of the underlying network and bounds on the Hessian of the objective function, we determine the algorithm parameters that guarantee the fastest convergence and characterize situations when significant speed-ups can be obtained over the standard gradient method. Furthermore, we quantify how the performance of the gradient method and its accelerated counterpart are affected by uncertainty in the problem data, and conclude that in most cases our proposed method outperforms gradient descent. Finally, we apply the proposed technique to three engineering problems: resource allocation under network-wide budget constraints, distributed averaging, and Internet congestion control. In all cases, we demonstrate that our algorithm converges more rapidly than alternative algorithms reported in the literature.

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。

↑