ICML 2019oral0 citations

Curvature-Exploiting Acceleration of Elastic Net Computations

Vien Mai, Mikael Johansson

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.

BibTeX
@InProceedings{pmlr-v97-mai19a,
  title = 	 {Curvature-Exploiting Acceleration of Elastic Net Computations},
  author =       {Mai, Vien and Johansson, Mikael},
  booktitle = 	 {Proceedings of the 36th International Conference on Machine Learning},
  pages = 	 {4294--4303},
  year = 	 {2019},
  editor = 	 {Chaudhuri, Kamalika and Salakhutdinov, Ruslan},
  volume = 	 {97},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {09--15 Jun},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v97/mai19a/mai19a.pdf},
  url = 	 {https://proceedings.mlr.press/v97/mai19a.html},
  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.}
}
Curvature-Exploiting Acceleration of Elastic Net Computations · ICML 2019