High-dimensional sparse trigonometric approximation in the uniform norm and consequences for sampling recovery.
Moritz MoellerSerhii A. StasyukTino UllrichPublished in: CoRR (2024)
Keyphrases
- high dimensional
- uniform sampling
- low rank approximation
- sparse data
- compressive sampling
- parameter space
- compressive sensing
- high dimensionality
- low dimensional
- sparse sampling
- low rank matrices
- dimensionality reduction
- feature space
- singular value decomposition
- orthogonal matching pursuit
- variable selection
- high dimension
- nearest neighbor
- compressed sensing
- sample size
- convex functions
- similarity search
- input space
- metric space
- group lasso
- regularized least squares
- objective function
- gene expression data
- closed form
- sparse representation
- low rank
- error bounds
- basis functions
- monte carlo
- feature selection
- high dimensional data
- additive models
- mixed norm
- random projections
- np hard
- support vector machine
- generalized linear models
- kernel function
- structured sparsity
- lp norm
- sparse approximation