arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 0706.0720cs.ITmath.IT
收藏

通信受限环境下带反馈的泛分位数估计

Universal Quantile Estimation with Feedback in the Communication-Constrained Setting

Ram Rajagopal, Martin J. Wainwright

摘要:

我们考虑以下分散统计推断问题:给定独立同分布。从未知分布的样本,估计一个任意的分位数受到限制的位交换。我们分析了一个标准的融合为基础的架构,其中每个$m$传感器发送一个单一的位到融合中心,这反过来又被允许发送一些$k$位的反馈。假设每个$\nodenum$传感器接收$n$观测值,最优集中式协议产生均方误差衰减为$\order(1/[n m])$。我们开发并分析了各种分散式协议的性能,并与这种集中式黄金标准进行了比较。首先,我们描述了一个分散的协议的基础上$k = \log(\nodenum)$位的反馈是强一致的,并实现了相同的渐近MSE的集中式最优。其次,我们描述和分析了一个分散的协议的基础上,只有一个单一的位($k=1$)的反馈。对于与$m$无关的步长,它实现了$\order[1/(n \sqrt{m})]$阶的渐近MSE,而对于衰减为$1/\sqrt{m}$的步长,它实现了与集中式最优值相同的MSE中的$\order(1/[n m])$衰减。我们的理论结果是补充模拟,说明这些不同的协议之间的权衡。

英文摘要:

We consider the following problem of decentralized statistical inference: given i.i.d. samples from an unknown distribution, estimate an arbitrary quantile subject to limits on the number of bits exchanged. We analyze a standard fusion-based architecture, in which each of $m$ sensors transmits a single bit to the fusion center, which in turn is permitted to send some number $k$ bits of feedback. Supposing that each of $\nodenum$ sensors receives $n$ observations, the optimal centralized protocol yields mean-squared error decaying as $\order(1/[n m])$. We develop and analyze the performance of various decentralized protocols in comparison to this centralized gold-standard. First, we describe a decentralized protocol based on $k = \log(\nodenum)$ bits of feedback that is strongly consistent, and achieves the same asymptotic MSE as the centralized optimum. Second, we describe and analyze a decentralized protocol based on only a single bit ($k=1$) of feedback. For step sizes independent of $m$, it achieves an asymptotic MSE of order $\order[1/(n \sqrt{m})]$, whereas for step sizes decaying as $1/\sqrt{m}$, it achieves the same $\order(1/[n m])$ decay in MSE as the centralized optimum. Our theoretical results are complemented by simulations, illustrating the tradeoffs between these different protocols.

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。

↑