Greedy Output Approximation: Towards Efficient Structured Pruning for LLMs Without Retraining.

Jianwei Li Yijun Dong Qi Lei

Published in: CoRR (2024)

Keyphrases

data mining
search space
greedy algorithm
approximation error
machine learning
computationally expensive
effective pruning
dynamic programming
cost effective
closed form
efficient computation
pruning method