Iterative hard thresholding methods for \(l_0\) regularized convex cone programming (Q463721)

From MaRDI portal
scientific article
Language Label Description Also known as
English
Iterative hard thresholding methods for \(l_0\) regularized convex cone programming
scientific article

    Statements

    Iterative hard thresholding methods for \(l_0\) regularized convex cone programming (English)
    0 references
    0 references
    17 October 2014
    0 references
    The author presents an iterative hard thresholding (IHT) method and its variant for solving a special \(l_0\) regularized box constrained convex programming. The iteration complexity of the IHT method for finding an \(\epsilon\)-local-optimal solution of the problem is obtained. Furthermore, the author develops a method for solving \(l_0\) regularized convex cone programming by applying the IHT method to its quadratic penalty relation and establishes its iteration complexity for finding an \(\epsilon\)-approximate local minimizer of the problem.
    0 references
    0 references
    0 references
    0 references
    0 references
    sparse approximation
    0 references
    iterative hard thresholding method
    0 references
    \(l_0\) regularization
    0 references
    box constrained convex programming
    0 references
    convex cone programming
    0 references
    iteration complexity
    0 references
    0 references
    0 references