English

On Identifiability of Nonnegative Matrix Factorization

Machine Learning 2018-03-14 v1 Machine Learning

Abstract

In this letter, we propose a new identification criterion that guarantees the recovery of the low-rank latent factors in the nonnegative matrix factorization (NMF) model, under mild conditions. Specifically, using the proposed criterion, it suffices to identify the latent factors if the rows of one factor are \emph{sufficiently scattered} over the nonnegative orthant, while no structural assumption is imposed on the other factor except being full-rank. This is by far the mildest condition under which the latent factors are provably identifiable from the NMF model.

Keywords

Cite

@article{arxiv.1709.00614,
  title  = {On Identifiability of Nonnegative Matrix Factorization},
  author = {Xiao Fu and Kejun Huang and Nicholas D. Sidiropoulos},
  journal= {arXiv preprint arXiv:1709.00614},
  year   = {2018}
}
R2 v1 2026-06-22T21:31:28.062Z