Subspace Learning with Partial Information

The goal of subspace learning is to find a $k$-dimensional subspace of $\mathbb{R}^d$, 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 $r \le d$ attributes from each instance vector. We propose several efficient algorithms for this task, and analyze their sample complexity. [abs] [ pdf ][ bib ] &copy JMLR 2016. ( edit, beta )

Authors

• Alon Gonen
• Dan Rosenbaum
• Yonina C. Eldar Weizmann Institute of Science, Rehovot, Israel
• Shai Shalev-Shwartz The Hebrew University

Keywords

No keywords are indexed for this paper.