arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.04057math.PR
收藏

均匀相关衰减高斯观测值的大样本协方差阵

Large Sample Covariance Matrices of Gaussian Observations with Uniform Correlation Decay

Michael Fleermann, Johannes Heiny

摘要:

我们推导出了$V_n=\frac{1}{n}XX^T$形式的样本协方差阵的Marchenko-Pastur(MP)定律,其中$X$是$p\times n$数据矩阵,而$p/n\to y\in(0,\infty)$是$n,p \to \infty$。我们假设$X$中的数据来自相关的联合正态分布。特别地,相关性在$X$的行和列之间都起作用,并且我们不假设特定的相关性结构,例如可分离的依赖关系。相反,我们假设相关性以$a_n/n$的速度一致收敛到零,其中$a_n$可以温和地增长到无穷大。我们采用矩的方法紧紧:我们确定的确切条件的增长$a_n$,这将保证的经验谱分布(ESD)的时刻收敛到MP时刻。如果条件不满足,我们可以构造一个系综,其中几乎所有的ESD时刻都是发散的。我们还研究了在$C/n^δ$的一致相关界下$V_n$的算子范数,其中$C,δ>0$是固定的,并观察到在$δ=1$处的相变.特别是,只有在$δ>1$的情况下才能保证算子范数收敛到MP分布支持的最大值。分析导致一个例子,MP法几乎肯定成立,但运营商的规范仍然是随机的限制,我们提供了确切的极限分布。

英文摘要:

We derive the Marchenko-Pastur (MP) law for sample covariance matrices of the form $V_n=\frac{1}{n}XX^T$, where $X$ is a $p\times n$ data matrix and $p/n\to y\in(0,\infty)$ as $n,p \to \infty$. We assume the data in $X$ stems from a correlated joint normal distribution. In particular, the correlation acts both across rows and across columns of $X$, and we do not assume a specific correlation structure, such as separable dependencies. Instead, we assume that correlations converge uniformly to zero at a speed of $a_n/n$, where $a_n$ may grow mildly to infinity. We employ the method of moments tightly: We identify the exact condition on the growth of $a_n$ which will guarantee that the moments of the empirical spectral distributions (ESDs) converge to the MP moments. If the condition is not met, we can construct an ensemble for which all but finitely many moments of the ESDs diverge. We also investigate the operator norm of $V_n$ under a uniform correlation bound of $C/n^δ$, where $C,δ>0$ are fixed, and observe a phase transition at $δ=1$. In particular, convergence of the operator norm to the maximum of the support of the MP distribution can only be guaranteed if $δ>1$. The analysis leads to an example for which the MP law holds almost surely, but the operator norm remains stochastic in the limit, and we provide its exact limiting distribution.

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。

↑