Search Results for author:
Found 3 papers, 1 papers with code
TED: Accelerate Model Training by Internal Generalization
TED uses an optimization objective based on Internal Generalization Distance (IGD), measuring changes in IG before and after pruning to align with true generalization performance and achieve implicit regularization.
LNPT: Label-free Network Pruning and Training
Pruning before training enables the deployment of neural networks on smart devices.
SEVEN: Pruning Transformer Model by Reserving Sentinels
We utilize this design to dynamically assess the importance scores of weights. SEVEN is introduced by us, which particularly favors weights with consistently high sensitivity, i. e., weights with small gradient noise.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
