← Search

Kevin Luo

2 accepted papers

2024

No Free Prune: Information-Theoretic Barriers to Pruning at Initialization

ICML 2024poster

The existence of “lottery tickets” (Frankle & Carbin, 2018) at or near initialization raises the tantalizing question of whether large models are necessary in deep learning, or whether sparse networks can be quickly identified and trained without ever training the dense models that contain them. How…

Cited by 5SourcePDFScholar