AGD: an Auto-switchable Optimizer using Stepwise Gradient Difference for Preconditioning Matrix.
Yun YueZhiling YeJiadi JiangYongchao LiuKe ZhangPublished in: NeurIPS (2023)
Keyphrases
- structure tensor
- singular value decomposition
- neural network
- query optimization
- edge preserving
- image processing
- positive definite
- early vision
- linear algebra
- bundle adjustment
- optimization algorithm
- primal dual
- covariance matrix
- singular values
- query optimizer
- database management systems
- optical flow
- gradient vector