Login / Signup
Random-LTD: Random and Layerwise Token Dropping Brings Efficient Training for Large-scale Transformers.
Zhewei Yao
Xiaoxia Wu
Conglong Li
Connor Holmes
Minjia Zhang
Cheng Li
Yuxiong He
Published in:
CoRR (2022)
Keyphrases
</>
real life
uniformly distributed
training process
website
e learning
knowledge base
decision trees
face recognition
bayesian networks
information technology
data sets
evolutionary algorithm
online learning
test set
computationally expensive
phase transition
randomly generated
computer vision