A symmetric rank-one quasi-Newton method for nonnegative matrix factorization
From MaRDI portal
Publication:469969
Abstract: As we all known, the nonnegative matrix factorization (NMF) is a dimension reduction method that has been widely used in image processing, text compressing and signal processing etc. In this paper, an algorithm for nonnegative matrix approximation is proposed. This method mainly bases on the active set and the quasi-Newton type algorithm, by using the symmetric rank-one and negative curvature direction technologies to approximate the Hessian matrix. Our method improves the recent results of those methods in [Pattern Recognition, 45(2012)3557-3565; SIAM J. Sci. Comput., 33(6)(2011)3261-3281; Neural Computation, 19(10)(2007)2756-2779, etc.]. Moreover, the object function decreases faster than many other NMF methods. In addition, some numerical experiments are presented in the synthetic data, imaging processing and text clustering. By comparing with the other six nonnegative matrix approximation methods, our experiments confirm to our analysis.
Recommendations
- Image processing using Newton-based algorithm of nonnegative matrix factorization
- Fast nonnegative matrix factorization: an active-set-like method and comparisons
- Adaptive computation of the symmetric nonnegative matrix factorization (SymNMF)
- Efficient nonnegative matrix factorization via projected Newton method
- scientific article; zbMATH DE number 7404610
Cites work
- scientific article; zbMATH DE number 1818892 (Why is no real title available?)
- scientific article; zbMATH DE number 961607 (Why is no real title available?)
- A symmetric rank-one quasi-Newton line-search method using negative curvature directions
- Algorithms and applications for approximate nonnegative matrix factorization
- Efficient nonnegative matrix factorization via projected Newton method
- Fast Projection‐Based Methods for the Least Squares Nonnegative Matrix Approximation Problem
- Fast nonnegative matrix factorization: an active-set-like method and comparisons
- Learning the parts of objects by non-negative matrix factorization
- Nonnegative Matrix Factorization Based on Alternating Nonnegativity Constrained Least Squares and Active Set Method
- Projected Gradient Methods for Nonnegative Matrix Factorization
- Projected Newton Methods for Optimization Problems with Simple Constraints
Cited in
(10)- Iterative algorithm for the Q-weighted nonnegative matrix factorization
- Adaptive computation of the symmetric nonnegative matrix factorization (SymNMF)
- Computing symmetric nonnegative rank factorizations
- On reduced rank nonnegative matrix factorization for symmetric nonnegative matrices
- Active set type algorithms for nonnegative matrix factorization in hyperspectral unmixing
- Image processing using Newton-based algorithm of nonnegative matrix factorization
- Off-diagonal symmetric nonnegative matrix factorization
- scientific article; zbMATH DE number 7404610 (Why is no real title available?)
- Efficient method for symmetric nonnegative matrix factorization with an approximate augmented Lagrangian scheme
- Non-negative low-rank approximations for multi-dimensional arrays on statistical manifold
This page was built for publication: A symmetric rank-one quasi-Newton method for nonnegative matrix factorization
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q469969)
