arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.07669math.STcs.NAmath.NAstat.TH

用于矩阵扰动分析的精确$\boldsymbol{\u0398}$正弦公式及其应用

An exact $\sinΘ$ formula for matrix perturbation analysis and its applications

He Lyu, Rongrong Wang

AI总结:

该研究建立了矩阵扰动下奇异子空间间$\u0398$正弦距离的精确公式,揭示扰动传递机制,并据此推导了SVD扰动相关的多项新结果,涵盖奇异向量扰动紧界、PCA稳定性分析及奇异值阈值算子误差界。

摘要:

本文建立了一组用于计算原始奇异子空间与扰动后奇异子空间之间$\u0398$正弦距离的实用公式。这些公式清晰揭示了原始矩阵的扰动如何传递到奇异向量与奇异子空间中,为分析这类扰动提供了直接途径。在此基础上,本文推导了一系列与奇异值分解(SVD)扰动相关的新结果,包括高斯噪声下奇异向量扰动误差的$\u2113_{2,\u221e}$范数的更紧界、主成分分析(PCA)的全新稳定性分析,以及奇异值阈值算子的误差界。针对后两项结果,本文考虑了最具一般性的满秩矩形矩阵情形。

英文摘要:

In this paper, we establish a useful set of formulae for the $\sinΘ$ distance between the original and the perturbed singular subspaces. These formulae explicitly show that how the perturbation of the original matrix propagates into singular vectors and singular subspaces, thus providing a direct way of analyzing them. Following this, we derive a collection of new results on SVD perturbation related problems, including a tighter bound on the $\ell_{2,\infty}$ norm of the singular vector perturbation errors under Gaussian noise, a new stability analysis of the Principal Component Analysis and an error bound on the singular value thresholding operator. For the latter two, we consider the most general rectangular matrices with full matrix rank.

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。

↑