English

Linear Regression with Limited Observation

Machine Learning 2012-06-22 v1 Machine Learning

Abstract

We consider the most common variants of linear regression, including Ridge, Lasso and Support-vector regression, in a setting where the learner is allowed to observe only a fixed number of attributes of each example at training time. We present simple and efficient algorithms for these problems: for Lasso and Ridge regression they need the same total number of attributes (up to constants) as do full-information algorithms, for reaching a certain accuracy. For Support-vector regression, we require exponentially less attributes compared to the state of the art. By that, we resolve an open problem recently posed by Cesa-Bianchi et al. (2010). Experiments show the theoretical bounds to be justified by superior performance compared to the state of the art.

Keywords

Cite

@article{arxiv.1206.4678,
  title  = {Linear Regression with Limited Observation},
  author = {Elad Hazan and Tomer Koren},
  journal= {arXiv preprint arXiv:1206.4678},
  year   = {2012}
}

Comments

ICML2012

R2 v1 2026-06-21T21:22:53.972Z