In a combinatorial toy setting, winning lottery tickets preserve families of compatible feature locations in early feature space that balance proximity to final codes with low interference, rather than specific weight subnetworks.
arXiv preprint arXiv:2210.03044 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2verdicts
UNVERDICTED 2representative citing papers
Post-training N:M activation pruning preserves generative performance in LLMs better than equivalent weight pruning, with the 8:16 pattern emerging as a practical hardware-friendly choice.
citing papers explorer
-
Toy Combinatorial Interpretability Models Reveal Lottery Tickets in Early Feature Space
In a combinatorial toy setting, winning lottery tickets preserve families of compatible feature locations in early feature space that balance proximity to final codes with low interference, rather than specific weight subnetworks.
-
Motivating Next-Gen Accelerators with Flexible (N:M) Activation Sparsity via Benchmarking Lightweight Post-Training Sparsification Approaches
Post-training N:M activation pruning preserves generative performance in LLMs better than equivalent weight pruning, with the 8:16 pattern emerging as a practical hardware-friendly choice.