activity
20202022
most citedWhy Do Deep Residual Networks Generalize Better than Deep Feedforward Networks? -- A Neural Tangent Kernel Perspective

32 citations · 36 across the 3 of their papers we have counts for

collaborators
Showing 2021Show all

1 paper · 1 filter

cs.LG2021★ 4 cited

Large Learning Rate Tames Homogeneity: Convergence and Balancing Effect

Yuqing Wang, Minshuo Chen, Tuo Zhao +1

Recent empirical advances show that training deep models with large learning rate often improves generalization performance. However, theoretical justifications on the benefits of…