Robustness of Minimum-Volume Nonnegative Matrix Factorization under an Expanded Sufficiently Scattered Condition
Machine Learning
2025-11-07 v1 Machine Learning
Numerical Analysis
Signal Processing
Numerical Analysis
Abstract
Minimum-volume nonnegative matrix factorization (min-vol NMF) has been used successfully in many applications, such as hyperspectral imaging, chemical kinetics, spectroscopy, topic modeling, and audio source separation. However, its robustness to noise has been a long-standing open problem. In this paper, we prove that min-vol NMF identifies the groundtruth factors in the presence of noise under a condition referred to as the expanded sufficiently scattered condition which requires the data points to be sufficiently well scattered in the latent simplex generated by the basis vectors.
Cite
@article{arxiv.2511.04291,
title = {Robustness of Minimum-Volume Nonnegative Matrix Factorization under an Expanded Sufficiently Scattered Condition},
author = {Giovanni Barbarino and Nicolas Gillis and Subhayan Saha},
journal= {arXiv preprint arXiv:2511.04291},
year = {2025}
}
Comments
38 pages, 4 figures