ML Anthology

Solving Ridge Regression Using Sketched Preconditioned SVRG

Alon Gonen, Francesco Orabona, Shai Shalev-Shwartz
ICML 2016 pp. 1397-1405
/icml/2016/gonen2016icml-solving/

Abstract

We develop a novel preconditioning method for ridge regression, based on recent linear sketching methods. By equipping Stochastic Variance Reduced Gradient (SVRG) with this preconditioning process, we obtain a significant speed-up relative to fast stochastic methods such as SVRG, SDCA and SAG.

PDF ICML Semantic Scholar

Cite

Text

Gonen et al. "Solving Ridge Regression Using Sketched Preconditioned SVRG." International Conference on Machine Learning, 2016.

Markdown

[Gonen et al. "Solving Ridge Regression Using Sketched Preconditioned SVRG." International Conference on Machine Learning, 2016.](https://mlanthology.org/icml/2016/gonen2016icml-solving/)

BibTeX

@inproceedings{gonen2016icml-solving,
  title     = {{Solving Ridge Regression Using Sketched Preconditioned SVRG}},
  author    = {Gonen, Alon and Orabona, Francesco and Shalev-Shwartz, Shai},
  booktitle = {International Conference on Machine Learning},
  year      = {2016},
  pages     = {1397-1405},
  volume    = {48},
  url       = {https://mlanthology.org/icml/2016/gonen2016icml-solving/}
}