2 papers
cs.LG2021
Layer-Parallel Training of Residual Networks with Auxiliary-Variable Networks
Qi Sun, Hexin Dong, Zewei Chen +3
Gradient-based methods for the distributed training of residual networks (ResNets) typically require a forward pass of the input data, followed by back-propagating the error gradie…
cs.LG2021
Towards Understanding the Generative Capability of Adversarially Robust Classifiers
Yao Zhu, Jiacheng Ma, Jiacheng Sun +3
Recently, some works found an interesting phenomenon that adversarially robust classifiers can generate good images comparable to generative models. We investigate this phenomenon…