O(k)-Equivariant Dimensionality Reduction on Stiefel Manifolds.
Andrew LeeHarlin LeeJose A. PereaNikolas SchonsheckMadeleine WeinsteinPublished in: CoRR (2023)
Keyphrases
- dimensionality reduction
- euclidean space
- low dimensional
- manifold learning
- data points
- euclidean distance
- high dimensional data
- high dimensional
- nonlinear dimensionality reduction
- low dimensional spaces
- feature space
- neighborhood preserving
- laplacian eigenmaps
- manifold structure
- higher dimensional
- embedding space
- diffusion maps
- riemannian manifolds
- feature extraction
- high dimensionality
- principal component analysis
- locally linear embedding
- pattern recognition
- data representation
- nonlinear manifold
- dimensionality reduction methods
- vector space
- pattern recognition and machine learning
- geodesic distance
- random projections
- metric space
- feature selection
- shape analysis
- rotation invariant
- principal components
- high dimensional spaces
- metric learning
- underlying manifold
- linear discriminant analysis
- cell complexes
- arbitrary dimension
- multidimensional scaling
- computer vision
- sparse representation
- matrix valued
- dimension reduction
- input space
- kernel pca
- latent space
- structure preserving
- data sets
- intrinsic dimensionality
- discriminant analysis
- lower dimensional
- covariance matrix