A variable fixing version of the two-block nonlinear constrained Gauss-Seidel algorithm for \(\ell _1\) -regularized least-squares.
Margherita PorcelliFrancesco RinaldiPublished in: Comput. Optim. Appl. (2014)
Keyphrases
- regularized least squares
- optimization algorithm
- objective function
- computational complexity
- linear programming
- gauss seidel
- particle swarm optimization
- learning algorithm
- expectation maximization
- linear systems
- convergence rate
- regression model
- sparse representation
- support vector machine svm
- probabilistic model
- support vector
- similarity measure