High-dimensional nonlinear approximation by parametric manifolds in Hölder-Nikol'skii spaces of mixed smoothness.
Dinh DungVan Kien NguyenPublished in: CoRR (2021)
Keyphrases
- high dimensional
- low dimensional manifolds
- low dimensional
- low dimensional spaces
- manifold learning
- discrete data
- latent space
- gaussian process latent variable models
- dimensionality reduction
- high dimensional feature space
- difference equations
- feature space
- high dimensional data
- similarity search
- riemannian manifolds
- nonlinear manifold
- kernel principal component analysis
- taylor series
- high dimension
- multi type
- euclidean space
- parameter space
- intrinsic dimensionality
- locally linear
- embedding space
- numerical integration
- metric space
- dimension reduction
- high dimensionality
- data points
- cost function
- high dimensional spaces
- linear approximation
- manifold embedding
- principal curves
- higher dimensional
- input space
- nearest neighbor
- lower dimensional
- approximation spaces
- manifold structure
- face images
- feature extraction
- nonlinear dimensionality reduction
- kernel pca
- data sets
- approximation algorithms
- latent variables
- kernel function
- objective function
- face recognition