Principal Component Analysis for Sparse High-Dimensional Data.
Tapani RaikoAlexander IlinJuha KarhunenPublished in: ICONIP (1) (2007)
Keyphrases
- high dimensional data
- principal component analysis
- dimensionality reduction
- low dimensional
- high dimensional
- sparse representation
- random projections
- linear discriminant analysis
- dimension reduction
- lower dimensional
- high dimensionality
- principal components
- high dimension
- subspace clustering
- similarity search
- nearest neighbor
- manifold learning
- high dimensions
- data points
- input space
- locally linear embedding
- feature space
- original data
- dimensional data
- subspace learning
- independent component analysis
- data analysis
- text data
- singular value decomposition
- nonlinear dimensionality reduction
- high dimensional datasets
- low rank
- sparse coding
- data sets
- variable selection
- high dimensional feature spaces
- face recognition
- discriminant analysis
- covariance matrix
- high dimensional spaces
- clustering high dimensional data
- high dimensional data sets
- feature extraction
- underlying manifold
- euclidean distance
- knn
- pattern recognition
- machine learning