In linear regression, LoRA can achieve lower excess risk than full fine-tuning when the pretraining-downstream difference is low-rank, and small LoRA ranks can improve generalization by acting as regularization.
The expressive power of low-rank adaptation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
LoRA vs. Full Fine-Tuning: A Theoretical Perspective
In linear regression, LoRA can achieve lower excess risk than full fine-tuning when the pretraining-downstream difference is low-rank, and small LoRA ranks can improve generalization by acting as regularization.