Newton Greedy Pursuit: A Quadratic Approximation Method for Sparsity-Constrained Optimization

@article{Yuan2014NewtonGP,
  title={Newton Greedy Pursuit: A Quadratic Approximation Method for Sparsity-Constrained Optimization},
  author={Xiao-Tong Yuan and Qingshan Liu},
  journal={2014 IEEE Conference on Computer Vision and Pattern Recognition},
  year={2014},
  pages={4122-4129}
}
First-order greedy selection algorithms have been widely applied to sparsity-constrained optimization. The main theme of this type of methods is to evaluate the function gradient in the previous iteration to update the non-zero entries and their values in the next iteration. In contrast, relatively less effort has been made to study the second-order greedy selection method additionally utilizing the Hessian information. Inspired by the classic constrained Newton method, we propose in this paper… CONTINUE READING