Provably Robust Blind Source Separation of Linear-Quadratic Near-Separable Mixtures
From MaRDI portal
Publication:5024389
DOI10.1137/20M1382878zbMath1482.65028arXiv2011.11966MaRDI QIDQ5024389
Nicolas Gillis, Christophe Kervazo, Nicolas Dobigeon
Publication date: 31 January 2022
Published in: SIAM Journal on Imaging Sciences (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2011.11966
separabilitynonnegative matrix factorizationlinear-quadratic modelsnonlinear blind source separationpure-pixel assumptionnonlinear hyperspectral unmixing
Analysis of algorithms and problem complexity (68Q25) Numerical aspects of computer graphics, image analysis, and computational geometry (65D18) Numerical methods for low-rank matrix approximation; matrix compression (65F55)
Cites Work
- Sparse regression using mixed norms
- Introductory lectures on convex optimization. A basic course.
- Principal component analysis.
- Blind Source Separation by Sparse Decomposition in a Signal Dictionary
- Computing a Nonnegative Matrix Factorization---Provably
- Successive Nonnegative Projection Algorithm for Robust Nonnegative Blind Source Separation
- Robust Near-Separable Nonnegative Matrix Factorization Using Linear Optimization
- On the Complexity of Nonnegative Matrix Factorization
- Linear-Quadratic Blind Source Separation Using NMF to Unmix Urban Hyperspectral Images
- Sparsity and Adaptivity for the Blind Separation of Partially Correlated Sources
- Nonnegative Matrix Factorization
- Semidefinite Programming Based Preconditioning for More Robust Near-Separable Nonnegative Matrix Factorization
- Learning the parts of objects by non-negative matrix factorization
- Supervised Nonlinear Spectral Unmixing Using a Postnonlinear Mixing Model for Hyperspectral Imagery
- A Convex Model for Nonnegative Matrix Factorization and Dimensionality Reduction on Physical Space
- Sparse and Unique Nonnegative Matrix Factorization Through Data Preprocessing
- Computing a nonnegative matrix factorization -- provably
