BriefGPT.xyz
May, 2019
广泛和深度神经网络的随机梯度下降的泛化界限
Generalization Bounds of Stochastic Gradient Descent for Wide and Deep Neural Networks
HTML
PDF
Yuan Cao, Quanquan Gu
TL;DR
研究深度神经网络的训练和泛化，在过度参数化的条件下，通过神经切向随机特征模型(NTRF)来限制泛化误差，并建立了神经切向内核(NTK)的联系。
Abstract
We study the training and generalization of
deep neural networks
(DNNs) in the
over-parameterized
regime, where the network width (i.e., number of hidden nodes per layer) is much larger than the number of trainin
→