Kernel spectral joint embeddings for high-dimensional noisy datasets using duo-landmark integral operators.
Xiucai DingRong MaPublished in: CoRR (2024)
Keyphrases
- landmark extraction
- high dimensional
- low dimensional
- dimensionality reduction
- high dimensional datasets
- feature space
- noisy data
- input space
- kernel function
- high dimensional data
- kernel space
- laplacian matrix
- benchmark datasets
- manifold learning
- high dimensionality
- vector space
- low dimensional spaces
- hilbert space
- similarity search
- gene expression data
- nearest neighbor
- data points
- additive models
- reproducing kernel hilbert space
- dimensional data
- parameter space
- high dimension
- experimental conditions
- variable selection
- euclidean space
- kernel methods
- distance measure
- normalized cut
- spectral analysis
- latent space
- hyperspectral
- feature selection
- high dimensional feature space
- hyperspectral imagery
- missing data
- multi dimensional
- support vector
- image segmentation