27th Conference of the International Linear Algebra Society (ILAS 2026)

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

May 18, 2026, 3:45 PM

25m

Torgersen Hall 1060 (Virginia Tech)

Minisymposium Talk Low-rank Matrix and Tensor Decompositions: Theory, Algorithms and Applications Low-rank Matrix and Tensor Decompositions: Theory, Algorithms and Applications

Speaker

Subhayan Saha (Universite de Mons)

Description

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.