Identifying Stable Components of Matrix /Tensor Factorizations via Low-Rank Approximation of Inter-Factorization Similarity.
Simon Van EyndhovenNico VervlietLieven De LathauwerSabine Van HuffelPublished in: EUSIPCO (2019)
Keyphrases
- low rank approximation
- singular value decomposition
- low rank
- tensor factorization
- frobenius norm
- nonnegative matrix factorization
- low rank matrix approximation
- matrix factorization
- high order
- tensor decomposition
- dimensionality reduction
- missing entries
- low rank matrix
- factorization method
- least squares
- singular values
- matrix completion
- similarity measure
- missing data
- measurement matrix
- linear combination
- reconstruction error
- higher order
- latent semantic indexing
- subspace learning
- iterative algorithms
- data matrix
- convex optimization
- distance measure
- negative matrix factorization
- spectral clustering
- high dimensional data
- data dependent
- adjacency matrix
- distance function
- principal component analysis
- semi supervised