Login / Signup
Train Big, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers.
Zhuohan Li
Eric Wallace
Sheng Shen
Kevin Lin
Kurt Keutzer
Dan Klein
Joey Gonzalez
Published in:
ICML (2020)
Keyphrases
</>
computational model
high level
experimental data
structured prediction
genetic algorithm
knowledge base
objective function
probability distribution
theoretical framework
data sets
neural network
feature selection
expert systems
probabilistic model
management system
simulation model