Low Rank Factorization for Compact Multi-Head Self-Attention.
Sneha MehtaHuzefa RangwalaNaren RamakrishnanPublished in: CoRR (2019)
Keyphrases
- low rank
- matrix factorization
- convex optimization
- missing data
- linear combination
- low rank matrix
- singular value decomposition
- matrix completion
- rank minimization
- non rigid structure from motion
- semi supervised
- high order
- matrix decomposition
- factorization methods
- high dimensional data
- minimization problems
- data matrix
- low rank matrices
- collaborative filtering
- data mining
- trace norm
- higher order
- pairwise