Adaptive Niching-Based Gradient-Accelerated Differential Evolution for High-Dimensional Nonconvex Optimization

Nonconvex optimization presents significant challenges in many fields, particularly in training deep neural networks (DNNs), where poor local minima can degrade generalization-especially with limited data. High-dimensional nonconvex optimization presents two central challenges: 1) effectively balancing global exploration with rapid local exploitation and 2) establishing convergence guarantees, particularly with sparse individuals under nonsmooth regularizations. To address these limitations, we