An iterative hard thresholding algorithm with improved convergence for low-rank tensor recovery.
José Henrique de Morais GoulartGérard FavierPublished in: EUSIPCO (2015)
Keyphrases
- low rank
- trace norm
- thresholding algorithm
- high order
- frobenius norm
- tensor decomposition
- missing data
- convex optimization
- matrix factorization
- linear combination
- matrix completion
- rank minimization
- semi supervised
- low rank matrix
- singular value decomposition
- kernel matrix
- matrix decomposition
- high dimensional data
- minimization problems
- low rank matrices
- non rigid structure from motion
- robust principal component analysis
- tensor factorization
- pairwise
- higher order
- low rank and sparse
- singular values
- data matrix
- feature selection
- high dimensional
- image segmentation