ICML 2018oral56 citations

An Iterative, Sketching-based Framework for Ridge Regression

Agniva Chowdhury, Jiasen Yang, Petros Drineas

Abstract

Ridge regression is a variant of regularized least squares regression that is particularly suitable in settings where the number of predictor variables greatly exceeds the number of observations. We present a simple, iterative, sketching-based algorithm for ridge regression that guarantees high-quality approximations to the optimal solution vector. Our analysis builds upon two simple structural results that boil down to randomized matrix multiplication, a fundamental and well-understood primitive of randomized linear algebra. An important contribution of our work is the analysis of the behavior of subsampled ridge regression problems when the ridge leverage scores are used: we prove that accurate approximations can be achieved by a sample whose size depends on the degrees of freedom of the ridge-regression problem rather than the dimensions of the design matrix. Our experimental evaluations verify our theoretical results on both real and synthetic data.

BibTeX
@InProceedings{pmlr-v80-chowdhury18a,
  title = 	 {An Iterative, Sketching-based Framework for Ridge Regression},
  author =       {Chowdhury, Agniva and Yang, Jiasen and Drineas, Petros},
  booktitle = 	 {Proceedings of the 35th International Conference on Machine Learning},
  pages = 	 {989--998},
  year = 	 {2018},
  editor = 	 {Dy, Jennifer and Krause, Andreas},
  volume = 	 {80},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {10--15 Jul},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v80/chowdhury18a/chowdhury18a.pdf},
  url = 	 {https://proceedings.mlr.press/v80/chowdhury18a.html},
  abstract = 	 {Ridge regression is a variant of regularized least squares regression that is particularly suitable in settings where the number of predictor variables greatly exceeds the number of observations. We present a simple, iterative, sketching-based algorithm for ridge regression that guarantees high-quality approximations to the optimal solution vector. Our analysis builds upon two simple structural results that boil down to randomized matrix multiplication, a fundamental and well-understood primitive of randomized linear algebra. An important contribution of our work is the analysis of the behavior of subsampled ridge regression problems when the ridge leverage scores are used: we prove that accurate approximations can be achieved by a sample whose size depends on the degrees of freedom of the ridge-regression problem rather than the dimensions of the design matrix. Our experimental evaluations verify our theoretical results on both real and synthetic data.}
}
An Iterative, Sketching-based Framework for Ridge Regression · ICML 2018