English

Classification with Low Rank and Missing Data

Machine Learning 2015-01-15 v1

Abstract

We consider classification and regression tasks where we have missing data and assume that the (clean) data resides in a low rank subspace. Finding a hidden subspace is known to be computationally hard. Nevertheless, using a non-proper formulation we give an efficient agnostic algorithm that classifies as good as the best linear classifier coupled with the best low-dimensional subspace in which the data resides. A direct implication is that our algorithm can linearly (and non-linearly through kernels) classify provably as well as the best classifier that has access to the full data.

Keywords

Cite

@article{arxiv.1501.03273,
  title  = {Classification with Low Rank and Missing Data},
  author = {Elad Hazan and Roi Livni and Yishay Mansour},
  journal= {arXiv preprint arXiv:1501.03273},
  year   = {2015}
}
R2 v1 2026-06-22T08:00:49.287Z