arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1311.5000math.STstat.TH
收藏

高维样本协方差阵特征向量经验谱分布的收敛速度

Convergence rates of eigenvector empirical spectral distribution of large dimensional sample covariance matrix

Ningning Xia, Yingli Qin, Zhidong Bai

摘要:

采用特征向量经验谱分布(VESD)研究协方差矩阵特征向量和特征值的极限行为。本文证明了样本协方差阵的期望VESD与Marčenko-Pastur分布函数之间的Kolmogorov距离是$O(N^{-1/2})$阶的。假设数据维度$n$与样本量$N$之比介于0和1之间,则在基础分布的有限10阶矩条件下建立该收敛速度。它还表明,对于任何固定的$η>0$,VESD的收敛速度是$O(N^{-1/4})$的概率和$O(N^{-1/4+η})$几乎肯定,需要有限的8阶矩的基础分布。

英文摘要:

The eigenvector Empirical Spectral Distribution (VESD) is adopted to investigate the limiting behavior of eigenvectors and eigenvalues of covariance matrices. In this paper, we shall show that the Kolmogorov distance between the expected VESD of sample covariance matrix and the Marčenko-Pastur distribution function is of order $O(N^{-1/2})$. Given that data dimension $n$ to sample size $N$ ratio is bounded between 0 and 1, this convergence rate is established under finite 10th moment condition of the underlying distribution. It is also shown that, for any fixed $η>0$, the convergence rates of VESD are $O(N^{-1/4})$ in probability and $O(N^{-1/4+η})$ almost surely, requiring finite 8th moment of the underlying 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。

↑