English

Subspace Learning with Partial Information

Machine Learning 2016-05-27 v2 Machine Learning

Abstract

The goal of subspace learning is to find a kk-dimensional subspace of Rd\mathbb{R}^d, such that the expected squared distance between instance vectors and the subspace is as small as possible. In this paper we study subspace learning in a partial information setting, in which the learner can only observe rdr \le d attributes from each instance vector. We propose several efficient algorithms for this task, and analyze their sample complexity

Keywords

Cite

@article{arxiv.1402.4844,
  title  = {Subspace Learning with Partial Information},
  author = {Alon Gonen and Dan Rosenbaum and Yonina Eldar and Shai Shalev-Shwartz},
  journal= {arXiv preprint arXiv:1402.4844},
  year   = {2016}
}
R2 v1 2026-06-22T03:12:01.086Z