activity
20182023
most citedHigh-dimensional Asymptotics of Feature Learning: How One Gradient Step Improves the Representation

11 citations · 14 across the 4 of their papers we have counts for

collaborators
Showing cs.ITShow all

1 paper · 1 filter

cs.IT2018

"Dependency Bottleneck" in Auto-encoding Architectures: an Empirical Study

Denny Wu, Yixiu Zhao, Yao-Hung Hubert Tsai +2

Recent works investigated the generalization properties in deep neural networks (DNNs) by studying the Information Bottleneck in DNNs. However, the mea- surement of the mutual info…