First-order perturbation analysis of low-rank tensor approximations based on the truncated HOSVD.
Emilio Rafael BaldaSher Ali CheemaJens SteinwandtMartin HaardtAmir WeissArie YeredorPublished in: ACSSC (2016)
Keyphrases
- low rank
- taylor series
- tensor decomposition
- high order
- singular value decomposition
- higher order
- convex optimization
- trace norm
- matrix factorization
- missing data
- linear combination
- low rank matrix
- higher order singular value decomposition
- matrix decomposition
- high dimensional data
- semi supervised
- matrix completion
- frobenius norm
- rank minimization
- kernel matrix
- data representation
- auxiliary information
- low rank matrices
- dimensionality reduction
- data matrix
- feature selection
- robust principal component analysis
- minimization problems
- collaborative filtering
- active learning