Divide-and-Conquer for Debiased $l_1$-norm Support Vector Machine in Ultra-high Dimensions.
Heng LianZengyan FanPublished in: J. Mach. Learn. Res. (2017)
Keyphrases
- high dimensions
- support vector machine
- lp norm
- high dimensional data
- high dimensional
- svm classifier
- high dimensional spaces
- multi class
- high speed
- support vector
- indexing schemes
- poor quality
- training set
- machine learning
- feature selection
- training data
- databases
- nearest neighbor
- feature vectors
- data points
- kernel function
- high dimensionality
- multiresolution
- feature space
- image processing