A Nonconvex Splitting Method for Symmetric Nonnegative Matrix Factorization: Convergence Analysis and Optimality
From MaRDI portal
Publication:4620847
DOI10.1109/TSP.2017.2679687zbMATH Open1414.94392arXiv1703.08267MaRDI QIDQ4620847FDOQ4620847
Authors: Songtao Lu, Mingyi Hong, Zhengdao Wang 
Publication date: 8 February 2019
Published in: IEEE Transactions on Signal Processing (Search for Journal in Brave)
Abstract: Symmetric nonnegative matrix factorization (SymNMF) has important applications in data analytics problems such as document clustering, community detection and image segmentation. In this paper, we propose a novel nonconvex variable splitting method for solving SymNMF. The proposed algorithm is guaranteed to converge to the set of Karush-Kuhn-Tucker (KKT) points of the nonconvex SymNMF problem. Furthermore, it achieves a global sublinear convergence rate. We also show that the algorithm can be efficiently implemented in parallel. Further, sufficient conditions are provided which guarantee the global and local optimality of the obtained solutions. Extensive numerical results performed on both synthetic and real data sets suggest that the proposed algorithm converges quickly to a local minimum solution.
Full work available at URL: https://arxiv.org/abs/1703.08267
Cited In (7)
- Four algorithms to solve symmetric multi-type non-negative matrix tri-factorization problem
- On reduced rank nonnegative matrix factorization for symmetric nonnegative matrices
- Efficient method for symmetric nonnegative matrix factorization with an approximate augmented Lagrangian scheme
- Quartic first-order methods for low-rank minimization
- A difference-of-convex approach for split feasibility with applications to matrix factorizations and outlier detection
- A convergent algorithm for bi-orthogonal nonnegative matrix tri-factorization
- A novel update rule of HALS algorithm for nonnegative matrix factorization and Zangwill's global convergence
This page was built for publication: A Nonconvex Splitting Method for Symmetric Nonnegative Matrix Factorization: Convergence Analysis and Optimality
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4620847)
