English

Curvature-Exploiting Acceleration of Elastic Net Computations

Optimization and Control 2019-01-25 v1 Machine Learning

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.

Keywords

Cite

@article{arxiv.1901.08523,
  title  = {Curvature-Exploiting Acceleration of Elastic Net Computations},
  author = {Vien V. Mai and Mikael Johansson},
  journal= {arXiv preprint arXiv:1901.08523},
  year   = {2019}
}

Comments

34 pages, 2 figures

R2 v1 2026-06-23T07:21:25.648Z