Greedy Layer Pruning: Decreasing Inference Time of Transformer Models.

David Peer Sebastian Stabinger Stefan Engl Antonio Jose Rodríguez-Sánchez

Published in: CoRR (2021)

Keyphrases

search space
random fields
fuzzy logic
prior knowledge
dynamic programming
probabilistic model
parameter estimation
machine learning algorithms
complex systems
statistical model
greedy algorithm
markov chain monte carlo