Using random matrix theory, the authors prove spectral separability of mean-shift spikes and asymptotic invariance of the original eigenspace, then introduce a knockoff-mean two-stage PCA procedure to remove the contamination.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Mean-Shift PCA by Knockoff Mean
Using random matrix theory, the authors prove spectral separability of mean-shift spikes and asymptotic invariance of the original eigenspace, then introduce a knockoff-mean two-stage PCA procedure to remove the contamination.