Multi-block Bregman proximal alternating linearized minimization and its application to sparse orthogonal nonnegative matrix factorization.
Masoud AhookhoshLe Thi Khanh HienNicolas GillisPanagiotis PatrinosPublished in: CoRR (2019)
Keyphrases
- nonnegative matrix factorization
- sparsity constraints
- negative matrix factorization
- probabilistic latent semantic indexing
- matrix factorization
- data representation
- objective function
- least squares
- nonnegative matrix
- spectral clustering
- data matrix
- document clustering
- sparse representation
- original data
- principal component analysis
- high dimensional
- minimization problems
- dimensionality reduction
- optical flow
- data sets