arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.11343math.OCcs.LGcs.MAmath.PR
收藏

存在依赖非周期通信的分布式基于梯度的optimization

Distributed gradient-based optimization in the presence of dependent aperiodic communication

Paderborn University(帕德博恩大学);Karlstad University(卡尔斯塔德大学);Hasso-Plattner-Institute, University of Potsdam(波茨坦大学哈索·普拉特纳研究院)

Adrian Redder, Arunselvan Ramaswamy, Holger Karl

摘要:

迭代分布式优化算法涉及多个代理,这些代理随着时间的推移彼此通信,以便最小化/最大化全局目标。在存在不可靠的通信网络的情况下,测量接收到的数据的新鲜度的信息量(AoI)可能很大,并且因此阻碍算法收敛。在本文中,我们研究了一般的分布式基于梯度的优化算法的收敛性的通信,既不定期发生,也不在随机独立的时间点。我们表明,收敛是有保证的随机变量与AoI过程是随机主导的随机变量有限的第一时刻。这改善了以前的要求有界性超过第一时刻。然后,我们引入随机强连接(SSC)网络,一种新的随机形式的强连通性的时变网络。我们展示:如果对于任何$p \ge0$,描述SSC网络中的代理之间的通信成功的过程是$α$ -与$n^{p-1}α(n)$可求和的混合,则相关联的AoI过程由具有有限$p$阶矩的随机变量随机支配。结合我们的第一个贡献,这意味着分布式随机梯度下降收敛的存在AoI,如果$α(n)$是可求和的。

英文摘要:

Iterative distributed optimization algorithms involve multiple agents that communicate with each other, over time, in order to minimize/maximize a global objective. In the presence of unreliable communication networks, the Age-of-Information (AoI), which measures the freshness of data received, may be large and hence hinder algorithmic convergence. In this paper, we study the convergence of general distributed gradient-based optimization algorithms in the presence of communication that neither happens periodically nor at stochastically independent points in time. We show that convergence is guaranteed provided the random variables associated with the AoI processes are stochastically dominated by a random variable with finite first moment. This improves on previous requirements of boundedness of more than the first moment. We then introduce stochastically strongly connected (SSC) networks, a new stochastic form of strong connectedness for time-varying networks. We show: If for any $p \ge0$ the processes that describe the success of communication between agents in a SSC network are $α$-mixing with $n^{p-1}α(n)$ summable, then the associated AoI processes are stochastically dominated by a random variable with finite $p$-th moment. In combination with our first contribution, this implies that distributed stochastic gradient descend converges in the presence of AoI, if $α(n)$ is summable.

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。

↑