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 1408.5294math.OCcs.ITmath.IT
收藏

分布式时变随机最优化与基于效用的通信

Distributed Time-Varying Stochastic Optimization and Utility-Based Communication

Andrea Simonetto, Leon Kester, Geert Leus

摘要:

我们设计了一个分布式异步随机ε梯度算法,使网络的计算和通信节点,以解决约束离散时间时变随机凸优化问题。每个节点在每个离散时间步只更新一次自己的决策变量。在一些假设下(其中,强凸性,梯度的Lipschitz连续性,持续激励),我们证明了该算法的渐近收敛到一个误差界,该误差界的大小与恒定步长的选择α,最优化问题的时间变异性,以及精度α有关.此外,收敛速度是线性的。然后,我们展示了如何计算局部随机ε梯度,也取决于随时间变化的噪声密度函数(PDF)的相邻节点,而不需要邻居发送这样的PDF在每个时间步。我们设计了基于实用程序的政策,让每个节点来决定是否发送或不最新的PDF,这保证了一个给定的用户指定的误差水平在计算的随机ε梯度。数值模拟显示所提出的方法的附加值和它的相关性的估计和控制的时变过程和网络系统。

英文摘要:

We devise a distributed asynchronous stochastic epsilon-gradient-based algorithm to enable a network of computing and communicating nodes to solve a constrained discrete-time time-varying stochastic convex optimization problem. Each node updates its own decision variable only once every discrete time step. Under some assumptions (among which, strong convexity, Lipschitz continuity of the gradient, persistent excitation), we prove the algorithm's asymptotic convergence in expectation to an error bound whose size is related to the constant stepsize choice alpha, the variability in time of the optimization problem, and to the accuracy epsilon. Moreover, the convergence rate is linear. Then, we show how to compute locally stochastic epsilon-gradients that depend also on the time-varying noise probability density function (PDF) of the neighboring nodes, without requiring the neighbors to send such PDFs at each time step. We devise utility-based policies to allow each node to decide whether to send or not the most up-to-date PDF, which guarantee a given user-specified error level epsilon in the computation of the stochastic epsilon-gradient. Numerical simulations display the added value of the proposed approach and its relevance for estimation and control of time-varying processes and networked systems.

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。

↑