A Counterexample for the Validity of Using Nuclear Norm as a Convex Surrogate of Rank.
Hongyang ZhangZhouchen LinChao ZhangPublished in: ECML/PKDD (2) (2013)
Keyphrases
- nuclear norm
- low rank
- low rank matrix
- minimization problems
- norm minimization
- singular values
- matrix completion
- convex optimization
- rank minimization
- low rank matrices
- singular value decomposition
- matrix factorization
- linear combination
- missing data
- convex relaxation
- kernel matrix
- semi supervised
- approximation methods
- high order
- total variation
- high dimensional data
- low rank approximation
- sparse matrix
- interior point methods
- sparse representation
- face recognition
- data matrix
- sparse coding
- low dimensional