An extended Newton-type algorithm for ℓ2-regularized sparse logistic regression and its efficiency for classifying large-scale datasets.
Rui WangNaihua XiuShenglong ZhouPublished in: J. Comput. Appl. Math. (2021)
Keyphrases
- detection algorithm
- optimal solution
- theoretical analysis
- experimental evaluation
- dynamic programming
- times faster
- cost function
- linear programming
- optimization algorithm
- significant improvement
- convex hull
- objective function
- synthetic datasets
- computational efficiency
- feature selection algorithms
- particle swarm optimization
- learning algorithm
- worst case
- k means
- simulated annealing
- synthetic and real datasets
- clustering method
- computational complexity
- search space
- lower bound
- preprocessing
- highly efficient
- gauss newton
- real world
- recognition algorithm
- tree structure
- least squares
- segmentation algorithm
- expectation maximization