On the complexity of nonnegative matrix factorization
Numerical Analysis
2007-09-27 v2 Information Retrieval
Abstract
Nonnegative matrix factorization (NMF) has become a prominent technique for the analysis of image databases, text databases and other information retrieval and clustering applications. In this report, we define an exact version of NMF. Then we establish several results about exact NMF: (1) that it is equivalent to a problem in polyhedral combinatorics; (2) that it is NP-hard; and (3) that a polynomial-time local search heuristic exists.
Cite
@article{arxiv.0708.4149,
title = {On the complexity of nonnegative matrix factorization},
author = {Stephen A. Vavasis},
journal= {arXiv preprint arXiv:0708.4149},
year = {2007}
}
Comments
Version 2 corrects small typos; adds ref to Cohen & Rothblum; adds ref to Gillis; clarifies reduction of NMF to int. simplex