Accelerating Attention through Gradient-Based Learned Runtime Pruning.

Zheng Li Soroush Ghodrati Amir Yazdanbakhsh Hadi Esmaeilzadeh Mingu Kang

Published in: CoRR (2022)

Keyphrases

pruning method
search space
focus of attention
real time
information retrieval
decision making
case study
face recognition
training data
least squares
effective pruning