A Convergence Analysis of Nesterov's Accelerated Gradient Method in Training Deep Linear Neural Networks.
Xin LiuWei TaoZhisong PanPublished in: CoRR (2022)
Keyphrases
- convergence analysis
- gradient method
- convergence rate
- neural network
- global convergence
- optimization methods
- step size
- genetic algorithm
- learning rate
- training set
- optimality conditions
- convergence speed
- supervised learning
- higher level
- negative matrix factorization
- primal dual
- semidefinite programming
- multiresolution
- approximation methods