10 citations · 26 across the 20 of their papers we have counts for
Showing 2021Show all
2 papers · 1 filter
cs.LG2021
Subspace Adversarial Training
Tao Li, Yingwen Wu, Sizhe Chen +2
Single-step adversarial training (AT) has received wide attention as it proved to be both efficient and robust. However, a serious problem of catastrophic overfitting exists, i.e.,…
cs.LG2021★ 2 cited
Low Dimensional Landscape Hypothesis is True: DNNs can be Trained in Tiny Subspaces
Tao Li, Lei Tan, Qinghua Tao +2
Deep neural networks (DNNs) usually contain massive parameters, but there is redundancy such that it is guessed that the DNNs could be trained in low-dimensional subspaces. In this…