Finite Sample Guarantees for PCA in Non-Isotropic and Data-Dependent Noise.
Namrata VaswaniPraneeth NarayanamurthyPublished in: CoRR (2017)
Keyphrases
- data dependent
- finite sample
- generalization bounds
- uniform convergence
- principal component analysis
- sample size
- reproducing kernel hilbert space
- statistical learning theory
- dimensionality reduction
- error bounds
- feature extraction
- nearest neighbor
- learning theory
- special case
- energy functional
- sufficient conditions
- data sets
- high dimensional
- pairwise
- face recognition
- feature selection