A convex model for non-negative matrix factorization and dimensionality reduction on physical space

Abstract

A collaborative convex framework for factoring a data matrix $X$ into a non-negative product $AS$, with a sparse coefficient matrix $S$, is proposed. We restrict the columns of the dictionary matrix $A$ to coincide with certain columns of the data matrix $X$, thereby guaranteeing a physically meaningful dictionary and dimensionality reduction. We use $l_{1,\infty }$ regularization to select the dictionary from the data and show this leads to an exact convex relaxation of $l_0$ in the case of distinct noise free data. We also show how to relax the restriction-to-$X$ constraint by initializing an alternating minimization approach with the solution of the convex model, obtaining a dictionary close to but not necessarily in $X$. We focus on applications of the proposed framework to hyperspectral endmember and abundances identification and also show an application to blind source separation of NMR data.

14 pages, 9 figures. EE and JX were supported by NSF grants {DMS-0911277}, {PRISM-0948247}, MM by the German Academic Exchange Service (DAAD), SO and MM by NSF grants {DMS-0835863}, {DMS-0914561}, {DMS-0914856} and ONR grant {N00014-08-1119}, and GS was supported by NSF, NGA, ONR, ARO, DARPA, and {NSSEFF.}

References in corpus (3)

• Submodular meets Spectral: Greedy Algorithms for Subset Selection, Sparse Approximation and Dictionary Selection
• C-HiLasso: A Collaborative Hierarchical Sparse Modeling Framework
• Network Flow Algorithms for Structured Sparsity

Cited by in corpus (42)

• Fast and Robust Recursive Algorithms for Separable Nonnegative Matrix Factorization
• Nonnegative Matrix Factorization for Signal and Data Analytics: Identifiability, Algorithms, and Applications
• Nonlinear hyperspectral unmixing with robust nonnegative matrix factorization
• Fast Conical Hull Algorithms for Near-separable Non-negative Matrix Factorization
• Factoring nonnegative matrices with linear programs
• Successive Nonnegative Projection Algorithm for Robust Nonnegative Blind Source Separation
• On Identifiability of Nonnegative Matrix Factorization
• Robust Near-Separable Nonnegative Matrix Factorization Using Linear Optimization
• Collaborative Total Variation: A General Framework for Vectorial TV Models
• Self-Dictionary Sparse Regression for Hyperspectral Unmixing: Greedy Pursuit and Pure Pixel Search are Related
• Blind and fully constrained unmixing of hyperspectral images
• Compressed Nonnegative Matrix Factorization is Fast and Accurate
• Generalized Separable Nonnegative Matrix Factorization
• Noisy Matrix Completion under Sparse Factor Models
• Introduction to Nonnegative Matrix Factorization
• Detection and tracking of gas plumes in LWIR hyperspectral video sequence data
• Robustness Analysis of Hottopixx, a Linear Programming Model for Factoring Nonnegative Matrices
• A Fast Gradient Method for Nonnegative Sparse Regression with Self Dictionary
• Accelerating Physics-Informed Neural Network Training with Prior Dictionaries
• Optimal Surface Marker Locations for Tumor Motion Estimation in Lung Cancer Radiotherapy
• Dictionary-based Tensor Canonical Polyadic Decomposition
• Memory-Efficient Convex Optimization for Self-Dictionary Separable Nonnegative Matrix Factorization: A Frank-Wolfe Approach
• Spatial Random Sampling: A Structure-Preserving Data Sketching Tool
• Enhancing Pure-Pixel Identification Performance via Preconditioning
• Relative Pairwise Relationship Constrained Non-negative Matrix Factorisation
• Maximum Volume Inscribed Ellipsoid: A New Simplex-Structured Matrix Factorization Framework via Facet Enumeration and Convex Optimization
• Spectral Unmixing with Multiple Dictionaries
• Provably robust blind source separation of linear-quadratic near-separable mixtures
• A New Geometric Approach to Latent Topic Modeling and Discovery
• Noisy Inductive Matrix Completion Under Sparse Factor Models
• Robust and Scalable Column/Row Sampling from Corrupted Big Data
• Greedy Frank-Wolfe Algorithm for Exemplar Selection
• Online Convex Matrix Factorization with Representative Regions
• On the Robustness of the Successive Projection Algorithm
• Endmember Extraction from Hyperspectral Images Using Self-Dictionary Approach with Linear Programming
• Near-separable Non-negative Matrix Factorization with ${\ell }_1$- and Bregman Loss Functions
• Feature Encoding in Band-limited Distributed Surveillance Systems
• Discriminative Robust Deep Dictionary Learning for Hyperspectral Image Classification
• A Method for Finding Structured Sparse Solutions to Non-negative Least Squares Problems with Applications
• Approximate Subspace-Sparse Recovery with Corrupted Data via Constrained ${\ell }_1$-Minimization
• Analysis on Non-negative Factorizations and Applications
• Dynamic SPECT reconstruction with temporal edge correlation