分布式估计的通信最优性权衡
Communication Optimality Trade-offs For Distributed Estimation
摘要:
本文提出了一种适用于无中心主节点的网络化多工作机系统的$\mathbf{C}$计算高效的$\mathbf{RE}$草书$\mathbf{D}$初始估计$\mathbf{O}$ n算法$\mathcal{CREDO}$。$\mathcal{CREDO}$被设计用于工作者节点旨在使用各个工作者节点处的分布式在线时间序列数据来协作地估计感兴趣的矢量参数的场景。各个工作者节点通过吸收最新的本地感测信息和来自在(可能稀疏的)时变通信图上交换的相邻工作者节点的估计来迭代地更新它们的参数估计。底层的工作者间通信协议是自适应的,使得通信随着时间的推移而越来越(概率上)稀疏。在工人间信息交换网络和感知模型的最小条件下,工人节点处的估计序列几乎必然收敛于真实参数。进一步,本文从估计序列的渐近协方差的角度刻画了$\mathcal{CREDO}$的性能,并具体地建立了最优渐近协方差的可逼近性。分析揭示了一个有趣的算法的通信成本之间的相互作用~ $\mathcal{C}_{t}$(超过$t$时间步长)和渐近协方差。最值得注意的是,它表明,$\mathcal{CREDO}$可以被设计为实现$Θ\left(\mathcal{C}_{t}^{-2+ζ}\right)$衰减的均方误差~($ζ>0$,任意小)在每个工作节点,显着提高了现有的$ Θ\left(\mathcal{C}_{t}^{-1}\right)$率。在模拟数据集和真实数据集上的仿真实例证明了$\mathcal{CREDO}$的通信效率。
英文摘要:
This paper proposes $\mathbf{C}$ommunication efficient $\mathbf{RE}$cursive $\mathbf{D}$istributed estimati$\mathbf{O}$n algorithm, $\mathcal{CREDO}$, for networked multi-worker setups without a central master node. $\mathcal{CREDO}$ is designed for scenarios in which the worker nodes aim to collaboratively estimate a vector parameter of interest using distributed online time-series data at the individual worker nodes. The individual worker nodes iteratively update their estimate of the parameter by assimilating latest locally sensed information and estimates from neighboring worker nodes exchanged over a (possibly sparse) time-varying communication graph. The underlying inter-worker communication protocol is adaptive, making communications increasingly (probabilistically) sparse as time progresses. Under minimal conditions on the inter-worker information exchange network and the sensing models, almost sure convergence of the estimate sequences at the worker nodes to the true parameter is established. Further, the paper characterizes the performance of $\mathcal{CREDO}$ in terms of asymptotic covariance of the estimate sequences and specifically establishes the achievability of optimal asymptotic covariance. The analysis reveals an interesting interplay between the algorithm's communication cost~$\mathcal{C}_{t}$ (over $t$ time-steps) and the asymptotic covariance. Most notably, it is shown that $\mathcal{CREDO}$ may be designed to achieve a $Θ\left(\mathcal{C}_{t}^{-2+ζ}\right)$ decay of the mean square error~($ζ>0$, arbitrarily small) at each worker node, which significantly improves over the existing $ Θ\left(\mathcal{C}_{t}^{-1}\right)$ rates. Simulation examples on both synthetic and real data sets demonstrate $\mathcal{CREDO}$'s communication efficiency.
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。