On Identifiability of Nonnegative Matrix Factorization

Abstract

In this letter, we propose a new identification criterion that guarantees the recovery of the low-rank latent factors in the nonnegative matrix factorization (NMF) model, under mild conditions. Specifically, using the proposed criterion, it suffices to identify the latent factors if the rows of one factor are \emph{sufficiently scattered} over the nonnegative orthant, while no structural assumption is imposed on the other factor except being full-rank. This is by far the mildest condition under which the latent factors are provably identifiable from the NMF model.

References in corpus (6)

• A Spectral Algorithm for Latent Dirichlet Allocation
• A Practical Algorithm for Topic Modeling with Provable Guarantees
• Fast Conical Hull Algorithms for Near-separable Non-negative Matrix Factorization
• Factoring nonnegative matrices with linear programs
• Robust Volume Minimization-Based Matrix Factorization for Remote Sensing and Document Clustering
• Anchor-Free Correlated Topic Modeling: Identifiability and Algorithm

Cited by in corpus (23)

• Hyperspectral Super-Resolution: A Coupled Tensor Factorization Approach
• Nonnegative Matrix Factorization for Signal and Data Analytics: Identifiability, Algorithms, and Applications
• Deep Spectrum Cartography: Completing Radio Map Tensors Using Learned Neural Models
• Blind Audio Source Separation with Minimum-Volume Beta-Divergence NMF
• Spectral Variability Aware Blind Hyperspectral Image Unmixing Based on Convex Geometry
• Generalized Separable Nonnegative Matrix Factorization
• Provably End-to-end Label-Noise Learning without Anchor Points
• Quaternion Non-negative Matrix Factorization: definition, uniqueness and algorithm
• Simplex-Structured Matrix Factorization: Sparsity-based Identifiability and Provably Correct Algorithms
• Nonlinear Multiview Analysis: Identifiability and Neural Network-assisted Implementation
• Recovering Joint Probability of Discrete Random Variables from Pairwise Marginals
• Polytopic Matrix Factorization: Determinant Maximization Based Criterion and Identifiability
• Majorization-minimization for Sparse Nonnegative Matrix Factorization with the $\beta$-divergence
• Near-Convex Archetypal Analysis
• Probabilistic Phase Labeling and Lattice Refinement for Autonomous Material Research
• Deep Nonnegative Matrix Factorization with Beta Divergences
• Mixed Membership Graph Clustering via Systematic Edge Query
• Bounded Simplex-Structured Matrix Factorization: Algorithms, Identifiability and Applications
• Checking the Sufficiently Scattered Condition using a Global Non-Convex Optimization Software
• Leveraging Joint-Diagonalization in Transform-Learning NMF
• Minimum-volume Multichannel Nonnegative matrix factorization for blind source separation
• Recovery of Joint Probability Distribution from one-way marginals: Low rank Tensors and Random Projections
• Crowdsourcing via Annotator Co-occurrence Imputation and Provable Symmetric Nonnegative Matrix Factorization