BriefGPT.xyz
Jun, 2020
稳健的次高斯主成分分析与宽度独立的谱范数填充
Robust Sub-Gaussian Principal Component Analysis and Width-Independent Schatten Packing
HTML
PDF
Arun Jambulapati, Jerry Li, Kevin Tian
TL;DR
研究开发了两种基于中心子高斯分布的降噪主成分分析算法,灵活应用于解决具有非代数结构矩的相关问题。同时定量地分析了算法的复杂性和置信度。
Abstract
We develop two methods for the following fundamental statistical task: given an $\epsilon$-corrupted set of $n$ samples from a $d$-dimensional
sub-gaussian distribution
, return an approximate top eigenvector of the
cova
→