奇异子空间的正规逼近与置信区域
Normal Approximation and Confidence Region of Singular Subspaces
摘要:
本文研究噪声矩阵具有独立同分布时奇异子空间的正规逼近问题。条目我们的贡献是三方面的。首先,我们推导出经验谱投影的一个显式表示公式。该公式是整洁的,并保持确定性矩阵扰动。其次,我们计算了经验奇异子空间与真奇异子空间之间的期望投影距离。我们的方法允许获得任意的$k$ -th阶近似的预期投影距离。第三,我们证明了投影距离的非渐近正态近似与不同程度的偏差校正。通过$\lceil \log(d_1+d_2)\rceil$阶偏差校正,在最佳信噪比(SNR)条件下渐近正态性成立,其中$d_1$和$d_2$表示矩阵大小。此外,它表明,高阶近似是不必要的,当$|d_1-d_2|=O((d_1+d_2)^{1/2})$。最后,我们提供了全面的模拟结果,值得我们的理论发现。与现有的结果不同,我们的方法是非渐近的,并建立了收敛速度。我们的方法允许秩$r$像$o((d_1+d_2)^{1/3})$一样快地发散。此外,我们的方法不需要本征间隙条件(除了SNR)和$d_1$和$d_2$之间没有约束。
英文摘要:
This paper is on the normal approximation of singular subspaces when the noise matrix has i.i.d. entries. Our contributions are three-fold. First, we derive an explicit representation formula of the empirical spectral projectors. The formula is neat and holds for deterministic matrix perturbations. Second, we calculate the expected projection distance between the empirical singular subspaces and true singular subspaces. Our method allows obtaining arbitrary $k$-th order approximation of the expected projection distance. Third, we prove the non-asymptotical normal approximation of the projection distance with different levels of bias corrections. By the $\lceil \log(d_1+d_2)\rceil$-th order bias corrections, the asymptotical normality holds under optimal signal-to-noise ration (SNR) condition where $d_1$ and $d_2$ denote the matrix sizes. In addition, it shows that higher order approximations are unnecessary when $|d_1-d_2|=O((d_1+d_2)^{1/2})$. Finally, we provide comprehensive simulation results to merit our theoretic discoveries. Unlike the existing results, our approach is non-asymptotical and the convergence rates are established. Our method allows the rank $r$ to diverge as fast as $o((d_1+d_2)^{1/3})$. Moreover, our method requires no eigen-gap condition (except the SNR) and no constraints between $d_1$ and $d_2$.
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。