Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Light
Dark
What Makes a Good Prune? Maximal Unstructured Pruning for Maximal Cosine Similarity
2024-01-16
· ICLR 2024 poster ·
anchor
Findings
IC-1336
MobileNetV2 (PyTorch pre-trained on ImageNet) exhibits a failure mode under global unstructured L1 pruning at the Pareto-optimal point, with its high kurtosis of kurtoses (64.40) causing very-low-magnitude layers to be entirely pruned and disconnect the network