高维高斯向量的典型相关系数:有限秩情形
Canonical correlation coefficients of high-dimensional Gaussian vectors: finite rank case
摘要:
考虑高斯向量$\mathbf{z}=(\mathbf{x}',\mathbf{y}')'$,由两个子向量$\mathbf{x}$和$\mathbf{y}$组成,分别具有维度$p$和$q$,其中$p$和$q$均与样本大小$n$成比例。用$Σ_{\mathbf{u}\mathbf{v}}$表示随机向量$\mathbf{u}$和$\mathbf{v}$的总体互协方差矩阵,用$S_{\mathbf{u}\mathbf{v}}$表示样本对应物。$\mathbf{x}$和$\mathbf{y}$之间的典型相关系数被称为典型相关矩阵$Σ_{\mathbf{x}\mathbf{x}}^{-1}Σ_{\mathbf{x}\mathbf{y}}Σ_{\mathbf{y}\mathbf{y}}^{-1}Σ_{\mathbf{y}\mathbf{x}}$的非零特征值的平方根。本文研究了$Σ_{\mathbf{x}\mathbf{y}}$具有有限秩$k$的情形,即存在$k$非零的典型相关系数,其平方记为$r_1\geq\cdots\geq r_k>0$ .我们研究$r_i,i=1,\ldots,k$的样本对应物,即样本典型相关矩阵$§_{\mathbf{x}\mathbf{x}}^{-1}§_{\mathbf{x}\mathbf{y}}§_{\mathbf{y}\mathbf{y}}^{-1}§_{\mathbf{y}\mathbf{x}}$的最大$k$特征值,记为$λ_1\geq\cdots\geq λ_k$。我们发现,存在一个阈值$r_c\in(0,1)$,这样,对于每个$i\in\{1,\ldots,k\}$,当$r_i\leq r_c$,$λ_i$几乎肯定收敛到样本典型相关矩阵的极限谱分布的右边缘,表示为$d_{+}$。当$r_i>r_c$时,$λ_i$在$(d_{+},1]$中具有几乎确定的极限。在适当的归一化条件下,我们还得到了$λ_i$的极限分布。具体地,如果$r_i>r_c$,则$λ_i$具有高斯型波动,并且如果$r_i<r_c$,则遵循Tracy-Widom分布。文中还讨论了所得结果的一些应用。
英文摘要:
Consider a Gaussian vector $\mathbf{z}=(\mathbf{x}',\mathbf{y}')'$, consisting of two sub-vectors $\mathbf{x}$ and $\mathbf{y}$ with dimensions $p$ and $q$ respectively, where both $p$ and $q$ are proportional to the sample size $n$. Denote by $Σ_{\mathbf{u}\mathbf{v}}$ the population cross-covariance matrix of random vectors $\mathbf{u}$ and $\mathbf{v}$, and denote by $S_{\mathbf{u}\mathbf{v}}$ the sample counterpart. The canonical correlation coefficients between $\mathbf{x}$ and $\mathbf{y}$ are known as the square roots of the nonzero eigenvalues of the canonical correlation matrix $Σ_{\mathbf{x}\mathbf{x}}^{-1}Σ_{\mathbf{x}\mathbf{y}}Σ_{\mathbf{y}\mathbf{y}}^{-1}Σ_{\mathbf{y}\mathbf{x}}$. In this paper, we focus on the case that $Σ_{\mathbf{x}\mathbf{y}}$ is of finite rank $k$, i.e. there are $k$ nonzero canonical correlation coefficients, whose squares are denoted by $r_1\geq\cdots\geq r_k>0$. We study the sample counterparts of $r_i,i=1,\ldots,k$, i.e. the largest $k$ eigenvalues of the sample canonical correlation matrix $§_{\mathbf{x}\mathbf{x}}^{-1}§_{\mathbf{x}\mathbf{y}}§_{\mathbf{y}\mathbf{y}}^{-1}§_{\mathbf{y}\mathbf{x}}$, denoted by $λ_1\geq\cdots\geq λ_k$. We show that there exists a threshold $r_c\in(0,1)$, such that for each $i\in\{1,\ldots,k\}$, when $r_i\leq r_c$, $λ_i$ converges almost surely to the right edge of the limiting spectral distribution of the sample canonical correlation matrix, denoted by $d_{+}$. When $r_i>r_c$, $λ_i$ possesses an almost sure limit in $(d_{+},1]$. We also obtain the limiting distribution of $λ_i$'s under appropriate normalization. Specifically, $λ_i$ possesses Gaussian type fluctuation if $r_i>r_c$, and follows Tracy-Widom distribution if $r_i<r_c$. Some applications of our results are also discussed.
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。