A sparse semismooth Newton based augmented Lagrangian method for large-scale support vector machines.
Dunbiao NiuChengjing WangPeipei TangQingsong WangEnbin SongPublished in: CoRR (2019)
Keyphrases
- support vector
- learning machines
- augmented lagrangian method
- total variation
- high dimensional
- convex optimization
- augmented lagrangian
- total variation regularization
- kernel function
- pairwise
- support vector machine
- kernel methods
- feature selection
- model selection
- loss function
- convergence speed
- training set
- locally adaptive
- gauss newton