Robustness of Minimum-Volume Nonnegative Matrix Factorization under an Expanded Sufficiently Scattered Condition
By: Giovanni Barbarino, Nicolas Gillis, Subhayan Saha
Potential Business Impact:
Makes computer analysis work better even with messy data.
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.
Similar Papers
A Provably-Correct and Robust Convex Model for Smooth Separable NMF
Numerical Analysis
Finds hidden patterns in data, even with noise.
A Globally Optimal Analytic Solution for Semi-Nonnegative Matrix Factorization with Nonnegative or Mixed Inputs
Machine Learning (CS)
Finds better patterns in mixed-sign data.
Non-Negative Matrix Factorization Using Non-Von Neumann Computers
Quantum Physics
New computer helps solve hard math problems faster.