arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.00211cs.ITmath.ITmath.STstat.TH
收藏

少量交互可最优地改进分布式非参数估计

A Few Interactions Improve Distributed Nonparametric Estimation, Optimally

Jingbo Liu

AI总结:

该研究针对分布式非参数密度估计问题,推导了单向与交互协议下的极小极大均方风险阶,证明少量超对数轮交互即可达到最优交互速率,并给出基于有偏伯努利变量估计的上下界证明。

摘要:

考虑在给定点处对未知β-Hölder光滑密度p_XY进行非参数估计的问题,其中X和Y均为d维。根据该分布生成无限独立同分布样本序列(X_i,Y_i),两个终端分别观测(X_i)和(Y_i)。为让Bob估计未知密度,二者可通过单向或交互方式交换k比特信息。我们证明,极小极大均方风险的阶在单向协议下为(k/log k)^(-2β/(d+2β)),在交互协议下为k^(-2β/(d+2β))。这种对数阶改进在参数化对应问题中不存在,因此可视为该问题非参数特性的结果。此外,仅需数轮交互即可达到交互极小极大速率:轮数的增长速度可慢至k的超对数(即逆迭代幂)。上界证明基于一种估计一对有偏伯努利变量联合分布的新型多轮方案,下界则建立在对有偏伯努利变量的对称强数据处理常数的精确估计之上。

英文摘要:

Consider the problem of nonparametric estimation of an unknown $β$-Hölder smooth density $p_{XY}$ at a given point, where $X$ and $Y$ are both $d$ dimensional. An infinite sequence of i.i.d.\ samples $(X_i,Y_i)$ are generated according to this distribution, and two terminals observe $(X_i)$ and $(Y_i)$, respectively. They are allowed to exchange $k$ bits either in oneway or interactively in order for Bob to estimate the unknown density. We show that the minimax mean square risk is order $\left(\frac{k}{\log k} \right)^{-\frac{2β}{d+2β}}$ for one-way protocols and $k^{-\frac{2β}{d+2β}}$ for interactive protocols. The logarithmic improvement is nonexistent in the parametric counterparts, and therefore can be regarded as a consequence of nonparametric nature of the problem. Moreover, a few rounds of interactions achieve the interactive minimax rate: the number of rounds can grow as slowly as the super-logarithm (i.e., inverse tetration) of $k$. The proof of the upper bound is based on a novel multi-round scheme for estimating the joint distribution of a pair of biased Bernoulli variables, and the lower bound is built on a sharp estimate of a symmetric strong data processing constant for biased Bernoulli variables.

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。

↑