深度宽神经网络的统计最优性【英文版】

英文标题：Statistical Optimality of Deep Wide Neural Networks中文摘要：本文研究了深度神经网络的泛化能力问题，探讨了其与神经切向核回归的关系，并分析了核的谱性质，得出了多层宽神经网络使用梯度下降等算法在早期停止时能够获得最佳性能的结论。英文摘要：In this paper, we consider the generalization ability of deep widefeedforward ReLU neural networks defined on a bounded domain $\mathcal X\subset \mathbb R^{d}$. We first demonstrate that the generalization ability ofthe neural network can be fully characterized by that of the corresponding deepneural tangent kernel (NTK) regression. We then investig