Curvature-Exploiting Acceleration of Elastic Net Computations

Abstract

This paper introduces an efficient second-order method for solving the elastic net problem. Its key innovation is a computationally efficient technique for injecting curvature information in the optimization process which admits a strong theoretical performance guarantee. In particular, we show improved run time over popular first-order methods and quantify the speed-up in terms of statistical measures of the data matrix. The improved time complexity is the result of an extensive exploitation of the problem structure and a careful combination of second-order information, variance reduction techniques, and momentum acceleration. Beside theoretical speed-up, experimental results demonstrate great practical performance benefits of curvature information, especially for ill-conditioned data sets.

Cite

Text

Mai and Johansson. "Curvature-Exploiting Acceleration of Elastic Net Computations." International Conference on Machine Learning, 2019.

Markdown

[Mai and Johansson. "Curvature-Exploiting Acceleration of Elastic Net Computations." International Conference on Machine Learning, 2019.](https://mlanthology.org/icml/2019/mai2019icml-curvatureexploiting/)

BibTeX

@inproceedings{mai2019icml-curvatureexploiting,
  title     = {{Curvature-Exploiting Acceleration of Elastic Net Computations}},
  author    = {Mai, Vien and Johansson, Mikael},
  booktitle = {International Conference on Machine Learning},
  year      = {2019},
  pages     = {4294-4303},
  volume    = {97},
  url       = {https://mlanthology.org/icml/2019/mai2019icml-curvatureexploiting/}
}