lottery-ticket-hypothesis

This paper introduces double-scoring, an augmented score-space parameterization for extracting strong lottery tickets from neural networks. It improves upon edge-popup and pruning-at-initialization baselines and reduces sensitivity to sparsity hyperparameters.

A paper investigating the reasons behind the success of overparameterization in neural networks, comparing the lottery ticket hypothesis with escape dimensions.

This paper introduces a resource-efficient pruning framework that identifies and removes parameters associated with unsafe behaviors in large language models while preserving utility. Using gradient-free attribution and the Lottery Ticket Hypothesis perspective, the method achieves significant reductions in unsafe generations and improved robustness against jailbreak attacks with minimal performance loss.