We consider online convex optimization (OCO) over a heterogeneous network with communication delay, where multiple workers together with a master execute a sequence of decisions to minimize the accumulation of time-varying global costs. The local data may not be independent or identically distributed, and the global cost functions may not be locally separable. Due to communication delay, neither the master nor the workers have in-time information about the current global cost function. We propose a new algorithm, termed Hierarchical OCO (HiOCO), which takes full advantage of the network heterogeneity in information timeliness and computation capacity to enable multi-step gradient descent at both the workers and the master. We analyze the impacts of the unique hierarchical architecture, multi-slot delay, and gradient estimation error to derive upper bounds on the dynamic regret of HiOCO, which measures the gap of costs between HiOCO and an offline globally optimal performance benchmark.
翻译:我们认为,在通信延迟的情况下,在线连接优化(OCO)是一个多式网络,多工人与一位主子一起执行一系列决定,以尽量减少时间变化的全球成本累积。当地数据可能不是独立或完全分布的,全球成本功能可能无法在本地分离。由于通信延迟,船长和工人都没有关于当前全球成本功能的实时信息。我们提出了一个新的算法,称为Hiorarchical OCO(HiOCO),它充分利用了网络在信息及时性和计算能力方面的差异性,使工人和主子都能够多步梯度梯度下降。我们分析了独特的等级结构、多行拖拉和梯度估计错误的影响,以获得HiOCO的动态遗憾的上限,后者衡量HiOCO与离线全球最佳绩效基准之间的成本差距。