Deterministic Conditions for Subspace Identifiability from Incomplete Sampling
Machine Learning
2016-02-22 v3 Machine Learning
Combinatorics
Abstract
Consider a generic -dimensional subspace of , , and suppose that we are only given projections of this subspace onto small subsets of the canonical coordinates. The paper establishes necessary and sufficient deterministic conditions on the subsets for subspace identifiability.
Cite
@article{arxiv.1410.0633,
title = {Deterministic Conditions for Subspace Identifiability from Incomplete Sampling},
author = {Daniel L. Pimentel-Alarcón and Robert D. Nowak and Nigel Boston},
journal= {arXiv preprint arXiv:1410.0633},
year = {2016}
}
Comments
To appear in Proc. of IEEE ISIT, 2015