Low-rank lottery tickets: finding efficient low-rank neural networks via matrix differential equations.
Steffen SchotthöferEmanuele ZangrandoJonas KuschGianluca CerutiFrancesco TudiscoPublished in: NeurIPS (2022)
Keyphrases
- low rank
- differential equations
- neural network
- linear combination
- convex optimization
- matrix factorization
- missing data
- singular value decomposition
- low rank matrix
- matrix decomposition
- matrix completion
- rank minimization
- kernel matrix
- trace norm
- high order
- semi supervised
- dynamical systems
- high dimensional data
- data matrix
- factorization methods
- singular values
- affinity matrix
- low rank and sparse
- low rank matrices
- artificial neural networks
- pairwise
- robust principal component analysis
- primal dual
- image compression
- collaborative filtering
- recommender systems
- pattern recognition
- image processing