Finite Sample Guarantees for PCA in Non-Isotropic and Data-Dependent Noise

Understand

This work obtains novel finite sample guarantees for Principal Component Analysis (PCA).

• These hold even when the corrupting noise is non-isotropic, and a part (or all of it) is data-dependent.
• Because of the latter, in general, the noise and the true data are correlated.
• The results in this work are a significant improvement over those given in our earlier work where this "correlated-PCA" problem was first studied.