\k{appa}-LoRA: Condition Numbers Reveal Which LoRA Matrices Worth Updating

By Jianghui Wang · Paper · cs.LG

Low-Rank Adaptation (LoRA) has become a widely adopted technique for efficient neural network fine-tuning, decomposing model updates into low-rank matrices. However, LoRA remains computationally costly because it updates all matrices uniformly, regardless of their actual contribu

Cs.lg

View original

HomeResourceLoading…