110 citations · 247 across the 6 of their papers we have counts for
Showing 2020Show all
2 papers · 1 filter
cs.LG2020★ 110 cited
How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks
Keyulu Xu, Mozhi Zhang, Jingling Li +3
We study how neural networks trained by gradient descent extrapolate, i.e., what they learn outside the support of the training distribution. Previous works report mixed empirical…
cs.LG2020★ 11 cited
Understanding Generalization in Deep Learning via Tensor Methods
Jingling Li, Yanchao Sun, Jiahao Su +2
Deep neural networks generalize well on unseen data though the number of parameters often far exceeds the number of training examples. Recently proposed complexity measures have pr…