A Quasi-Newton Proximal Splitting Method

Abstract

We describe efficient implementations of the proximity calculation for a useful class of functions; the implementations exploit the piece-wise linear nature of the dual problem. The second part of the paper applies the previous result to acceleration of convex minimization problems, and leads to an elegant quasi-Newton method. The optimization method compares favorably against state-of-the-art alternatives. The algorithm has extensive applications including signal processing, sparse regression and recovery, and machine learning and classification.

Cite

Text

Becker and Fadili. "A Quasi-Newton Proximal Splitting Method." Neural Information Processing Systems, 2012.

Markdown

[Becker and Fadili. "A Quasi-Newton Proximal Splitting Method." Neural Information Processing Systems, 2012.](https://mlanthology.org/neurips/2012/becker2012neurips-quasinewton/)

BibTeX

@inproceedings{becker2012neurips-quasinewton,
  title     = {{A Quasi-Newton Proximal Splitting Method}},
  author    = {Becker, Stephen and Fadili, Jalal},
  booktitle = {Neural Information Processing Systems},
  year      = {2012},
  pages     = {2618-2626},
  url       = {https://mlanthology.org/neurips/2012/becker2012neurips-quasinewton/}
}