most citedTable Pre-training: A Survey on Model Architectures, Pre-training Objectives, and Downstream Tasks

14 citations · 15 across the 3 of their papers we have counts for

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2022

Learning Rate Perturbation: A Generic Plugin of Learning Rate Schedule towards Flatter Local Minima

Hengyu Liu, Qiang Fu, Lun Du +4

Learning rate is one of the most important hyper-parameters that has a significant influence on neural network training. Learning rate schedules are widely used in real practice to…