Neural Collapse versus Low-rank Bias: Is Deep Neural Collapse Really Optimal?
Peter SúkeníkMarco MondelliChristoph LampertPublished in: CoRR (2024)
Keyphrases
- low rank
- neural network
- matrix factorization
- convex optimization
- missing data
- singular value decomposition
- linear combination
- matrix completion
- matrix decomposition
- high dimensional data
- high order
- rank minimization
- data sets
- principal component analysis
- machine learning
- collaborative filtering
- active learning
- trace norm
- pairwise
- non rigid structure from motion