64 citations · 68 across the 7 of their papers we have counts for
Showing cs.LGShow all
3 papers · 1 filter
cs.LG2022
Provably Learning Diverse Features in Multi-View Data with Midpoint Mixup
Muthu Chidambaram, Xiang Wang, Chenwei Wu +1
Mixup is a data augmentation technique that relies on training using random convex combinations of data points and their labels. In recent years, Mixup has become a standard primit…
cs.LG2022★ 1 cited
Understanding Edge-of-Stability Training Dynamics with a Minimalist Example
Xingyu Zhu, Zixuan Wang, Xiang Wang +2
Recently, researchers observed that gradient descent for deep neural networks operates in an ``edge-of-stability'' (EoS) regime: the sharpness (maximum eigenvalue of the Hessian) i…
cs.LG2021★ 3 cited
Towards Demystifying Representation Learning with Non-contrastive Self-supervision
Xiang Wang, Xinlei Chen, Simon S. Du +1
Non-contrastive methods of self-supervised learning (such as BYOL and SimSiam) learn representations by minimizing the distance between two views of the same image. These approache…