REVIEW 2 cited by
Movement Pruning: Adaptive Sparsity by Fine-Tuning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Magnitude pruning is a widely used strategy for reducing model size in pure supervised learning; however, it is less effective in the transfer learning regime that has become standard for state-of-the-art natural language processing applications. We propose the use of movement pruning, a simple, deterministic first-order weight pruning method that is more adaptive to pretrained model fine-tuning. We give mathematical foundations to the method and compare it to existing zeroth- and first-order pruning methods. Experiments show that when pruning large pretrained language models, movement pruning shows significant improvements in high-sparsity regimes. When combined with distillation, the approach achieves minimal accuracy loss with down to only 3% of the model parameters.
Forward citations
Cited by 2 Pith papers
-
Investigating Structural Pruning and Recovery Techniques for Compressing Multimodal Large Language Models: An Empirical Study
Structural pruning with finetuning plus hidden-state distillation recovers most performance in multimodal LLMs, with 5% of training data sufficient at moderate compression levels.
-
The Carbon Cost of Conversation, Sustainability in the Age of Language Models
A review-style essay that claims LLM training and use are environmentally expensive, but the quantitative evidence it presents is unreliable and internally inconsistent.
Discussion (0). Sign in to comment.