LoRA-XS: Low-Rank Adaptation with Extremely Small Number of Parameters.
Klaudia BalazyMohammadreza BanaeiKarl AbererJacek TaborPublished in: CoRR (2024)
Keyphrases
- low rank
- small number
- linear combination
- matrix factorization
- agent technology
- missing data
- low rank matrix
- singular value decomposition
- matrix completion
- convex optimization
- semi supervised
- rank minimization
- high dimensional data
- matrix decomposition
- minimization problems
- non rigid structure from motion
- low rank matrices
- high order
- trace norm
- expectation maximization
- higher order
- data analysis
- data mining