Shuffling-type gradient method with bandwidth-based step sizes for finite-sum optimization.
Yuqing LiangYang YangJinlan LiuDongpo XuPublished in: Neural Networks (2024)
Keyphrases
- gradient method
- step size
- faster convergence
- convergence rate
- line search
- cost function
- convergence speed
- optimization methods
- evolutionary programming
- optimization problems
- optimization algorithm
- global optimization
- neural network
- optimization method
- evolution strategy
- wavelet coefficients
- objective function
- multiscale
- computer vision