Thresholding tests based on affine LASSO to achieve non-asymptotic nominal level and high power under sparse and dense alternatives in high dimension.
Sylvain SardyJairo Diaz RodriguezCaroline GiacobinoPublished in: Comput. Stat. Data Anal. (2022)
Keyphrases
- high dimension
- high power
- feature selection
- real valued
- high dimensional
- feature space
- input space
- small sample
- high density
- support vector machine
- low power
- power supply
- denoising
- high dimensional data
- sample size
- image processing
- sparse representation
- variable selection
- power consumption
- kernel function
- input data
- edge detection
- worst case
- least squares
- machine learning