L0 Norm Based Dictionary Learning by Proximal Methods with Global Convergence

Abstract

Sparse coding and dictionary learning have seen their applications in many vision tasks, which usually is formulated as a non-convex optimization problem. Many iterative methods have been proposed to tackle such an optimization problem. However, it remains an open problem to have a method that is not only practically fast but also is globally convergent. In this paper, we proposed a fast proximal method for solving l0 norm based dictionary learning problems, and we proved that the whole sequence generated by the proposed method converges to a stationary point with sub-linear convergence rate. The benefit of having a fast and convergent dictionary learning method is demonstrated in the applications of image recovery and face recognition.

Cite

Text

Bao et al. "L0 Norm Based Dictionary Learning by Proximal Methods with Global Convergence." Conference on Computer Vision and Pattern Recognition, 2014. doi:10.1109/CVPR.2014.493

Markdown

[Bao et al. "L0 Norm Based Dictionary Learning by Proximal Methods with Global Convergence." Conference on Computer Vision and Pattern Recognition, 2014.](https://mlanthology.org/cvpr/2014/bao2014cvpr-l0/) doi:10.1109/CVPR.2014.493

BibTeX

@inproceedings{bao2014cvpr-l0,
  title     = {{L0 Norm Based Dictionary Learning by Proximal Methods with Global Convergence}},
  author    = {Bao, Chenglong and Ji, Hui and Quan, Yuhui and Shen, Zuowei},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2014},
  doi       = {10.1109/CVPR.2014.493},
  url       = {https://mlanthology.org/cvpr/2014/bao2014cvpr-l0/}
}