SINGULAR VECTOR PERTURBATION UNDER GAUSSIAN NOISE

被引:21
|
作者
Wang, Rongrong [1 ]
机构
[1] Univ British Columbia, Dept Math, Vancouver, BC V6T 1Z2, Canada
关键词
singular value decomposition; singular vector; Gaussian noise; nonasymptotic analysis; MODULATION CLASSIFICATION;
D O I
10.1137/130938177
中图分类号
O29 [应用数学];
学科分类号
070104 ;
摘要
We perform a nonasymptotic analysis on the singular vector distribution under Gaussian noise. In particular, we provide sufficient conditions on a matrix for its first few singular vectors to have near normal distribution. Our result can be used to facilitate the error analysis in linear dimension reduction.
引用
收藏
页码:158 / 177
页数:20
相关论文
共 50 条