77 citations · 129 across the 13 of their papers we have counts for
Showing 2019Show all
3 papers · 1 filter
cs.LG2019★ 77 cited
Enhanced Convolutional Neural Tangent Kernels
Zhiyuan Li, Ruosong Wang, Dingli Yu +4
Recent research shows that for training with loss, convolutional neural networks (CNNs) whose width (number of channels in convolutional layers) goes to infinity correspon…
cs.LG2019★ 13 cited
Harnessing the Power of Infinitely Wide Deep Nets on Small-data Tasks
Sanjeev Arora, Simon S. Du, Zhiyuan Li +3
Recent research shows that the following two models are equivalent: (a) infinitely wide neural networks (NNs) trained under l2 loss by gradient descent with infinitesimally small l…
cs.LG2019★ 15 cited
Simple and Effective Regularization Methods for Training on Noisily Labeled Data with Generalization Guarantee
Wei Hu, Zhiyuan Li, Dingli Yu
Over-parameterized deep neural networks trained by simple first-order methods are known to be able to fit any labeling of data. Such over-fitting ability hinders generalization whe…