Toward a unified theory of sparse dimensionality reduction in Euclidean space.
Jean BourgainJelani NelsonPublished in: CoRR (2013)
Keyphrases
- euclidean space
- low dimensional
- dimensionality reduction
- high dimensional
- data points
- euclidean distance
- embedding space
- metric space
- high dimensional data
- riemannian manifolds
- vector space
- shape analysis
- sparse representation
- nonlinear dimensionality reduction
- data representation
- manifold learning
- principal component analysis
- feature space
- dimensionality reduction methods
- reproducing kernel hilbert space
- dimensional euclidean space
- feature selection
- input space
- geodesic distance
- feature extraction
- multi dimensional scaling
- pairwise distances
- data sets
- principal components
- kernel pca
- distance function
- similarity search
- von neumann
- graph embedding
- lie group
- quadratic form