arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1901.09100cs.ITcs.LGmath.ITmath.STstat.MLstat.TH
收藏

估计相关性的通信复杂性

Communication Complexity of Estimating Correlations

Tel Aviv University(特拉维夫大学);Massachusetts Institute of Technology(麻省理工学院)

Uri Hadar, Jingbo Liu, Yury Polyanskiy, Ofer Shayevitz

摘要:

我们描述了以下分布式估计问题的通信复杂性。Alice和Bob观察到$ρ$相关单位方差(高斯或$\pm1$二进制)随机变量的无限多个iid副本,其中$ρ\in[-1,1]$未知。通过交互式地交换$k$位,Bob希望产生$ρ$的估计值$\hatρ$。我们表明,最好的可能的性能(优化的交互协议$Π$和估计$\hat ρ$)满足$\inf_{Π\hatρ}\sup_ρ\mathbb{E} [|ρ-\hatρ|^2] = \tfrac{1}{k} (\frac{1}{2 \ln 2} + o(1))$。奇怪的是,在我们的可交换性方案中,$k$中的样本数量是指数的;相比之下,交换$k$样本的朴素方案实现了相同的$Ω(1/k)$速率,但使用了次优的前因子。我们的协议实现最佳性能是单向的(非交互式)。我们还证明了$Ω(1/k)$界,即使$ρ$被限制到任何小的开放子区间的$[-1,1]$(即一个本地极小极大下界)。我们的证明技术依赖于对称的强数据处理不等式和各种张量化技术,从信息理论的交互式共同随机性提取。我们的结果也意味着一个$Ω(n)$下界的信息复杂性的间隙汉明问题,我们显示了一个直接的信息理论证明。

英文摘要:

We characterize the communication complexity of the following distributed estimation problem. Alice and Bob observe infinitely many iid copies of $ρ$-correlated unit-variance (Gaussian or $\pm1$ binary) random variables, with unknown $ρ\in[-1,1]$. By interactively exchanging $k$ bits, Bob wants to produce an estimate $\hatρ$ of $ρ$. We show that the best possible performance (optimized over interaction protocol $Π$ and estimator $\hat ρ$) satisfies $\inf_{Π\hatρ}\sup_ρ\mathbb{E} [|ρ-\hatρ|^2] = \tfrac{1}{k} (\frac{1}{2 \ln 2} + o(1))$. Curiously, the number of samples in our achievability scheme is exponential in $k$; by contrast, a naive scheme exchanging $k$ samples achieves the same $Ω(1/k)$ rate but with a suboptimal prefactor. Our protocol achieving optimal performance is one-way (non-interactive). We also prove the $Ω(1/k)$ bound even when $ρ$ is restricted to any small open sub-interval of $[-1,1]$ (i.e. a local minimax lower bound). Our proof techniques rely on symmetric strong data-processing inequalities and various tensorization techniques from information-theoretic interactive common-randomness extraction. Our results also imply an $Ω(n)$ lower bound on the information complexity of the Gap-Hamming problem, for which we show a direct information-theoretic proof.

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。

↑