Accelerating Gradient Descent for Over-Parameterized Asymmetric Low-Rank Matrix Sensing via Preconditioning.
Cheng ChengZiping ZhaoPublished in: ICASSP (2024)
Keyphrases
- belief state
- low rank matrix
- approximation methods
- conjugate gradient
- low rank
- iterative methods
- convex optimization
- loss function
- sparse matrix
- singular value decomposition
- convergence rate
- data sets
- matrix factorization
- primal dual
- pattern recognition
- missing data
- linear combination
- natural images
- image segmentation
- image processing