English

Least-squares methods for nonnegative matrix factorization over rational functions

Signal Processing 2023-05-31 v1 Computer Vision and Pattern Recognition Machine Learning

Abstract

Nonnegative Matrix Factorization (NMF) models are widely used to recover linearly mixed nonnegative data. When the data is made of samplings of continuous signals, the factors in NMF can be constrained to be samples of nonnegative rational functions, which allow fairly general models; this is referred to as NMF using rational functions (R-NMF). We first show that, under mild assumptions, R-NMF has an essentially unique factorization unlike NMF, which is crucial in applications where ground-truth factors need to be recovered such as blind source separation problems. Then we present different approaches to solve R-NMF: the R-HANLS, R-ANLS and R-NLS methods. From our tests, no method significantly outperforms the others, and a trade-off should be done between time and accuracy. Indeed, R-HANLS is fast and accurate for large problems, while R-ANLS is more accurate, but also more resources demanding, both in time and memory. R-NLS is very accurate but only for small problems. Moreover, we show that R-NMF outperforms NMF in various tasks including the recovery of semi-synthetic continuous signals, and a classification problem of real hyperspectral signals.

Keywords

Cite

@article{arxiv.2209.12579,
  title  = {Least-squares methods for nonnegative matrix factorization over rational functions},
  author = {Cécile Hautecoeur and Lieven De Lathauwer and Nicolas Gillis and François Glineur},
  journal= {arXiv preprint arXiv:2209.12579},
  year   = {2023}
}

Comments

13 pages

R2 v1 2026-06-28T02:05:38.821Z