DRPruning uses distributionally robust optimization with scaling-law-predicted reference losses and adaptive data ratios to improve domain-balanced performance recovery in LLM pruning and continued pretraining.
In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 13865–13881, Miami, Florida, USA
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DRPruning: Efficient Large Language Model Pruning through Distributionally Robust Optimization
DRPruning uses distributionally robust optimization with scaling-law-predicted reference losses and adaptive data ratios to improve domain-balanced performance recovery in LLM pruning and continued pretraining.