Robustness of Minimum-Volume Nonnegative Matrix Factorization under an Expanded Sufficiently Scattered Condition

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Barbarino, Giovanni, Gillis, Nicolas, Saha, Subhayan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917064863645696
author Barbarino, Giovanni
Gillis, Nicolas
Saha, Subhayan
author_facet Barbarino, Giovanni
Gillis, Nicolas
Saha, Subhayan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_04291
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Robustness of Minimum-Volume Nonnegative Matrix Factorization under an Expanded Sufficiently Scattered Condition
Barbarino, Giovanni
Gillis, Nicolas
Saha, Subhayan
Machine Learning
Numerical Analysis
Signal Processing
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.
title Robustness of Minimum-Volume Nonnegative Matrix Factorization under an Expanded Sufficiently Scattered Condition
topic Machine Learning
Numerical Analysis
Signal Processing
url https://arxiv.org/abs/2511.04291