Transition to Linearity of General Neural Networks with Directed Acyclic Graph Architecture

24 May 2022

Papers citing "Transition to Linearity of General Neural Networks with Directed Acyclic Graph Architecture"

3 / 3 papers shown

Title
Catapults in SGD: spikes in the training loss and their impact on generalization through feature learning Libin Zhu Chaoyue Liu Adityanarayanan Radhakrishnan M. Belkin 30 13 0 07 Jun 2023
On Emergence of Clean-Priority Learning in Early Stopped Neural Networks Chaoyue Liu Amirhesam Abedsoltan M. Belkin NoLa 17 4 0 05 Jun 2023
Toward Large Kernel Models Amirhesam Abedsoltan M. Belkin Parthe Pandit 28 16 0 06 Feb 2023