Poster
LoRA Training in the NTK Regime has No Spurious Local Minima
Uijeong Jang · Jason Lee · Ernest Ryu
Hall C 4-9 #1504
[
Abstract
]
[ Paper PDF ]
Oral
presentation:
Oral 6B Low Rank Learning
Thu 25 Jul 7:30 a.m. PDT — 8:30 a.m. PDT
[
Poster]
Thu 25 Jul 4:30 a.m. PDT
— 6 a.m. PDT
Thu 25 Jul 7:30 a.m. PDT — 8:30 a.m. PDT
Abstract:
Low-rank adaptation (LoRA) has become the standard approach for parameter-efficient fine-tuning of large language models (LLM), but our theoretical understanding of LoRA has been limited. In this work, we theoretically analyze LoRA fine-tuning in the neural tangent kernel (NTK) regime with $N$ data points, showing: (i) full fine-tuning (without LoRA) admits a low-rank solution of rank $r\lesssim \sqrt{N}$; (ii) using LoRA with rank $r\gtrsim \sqrt{N}$ eliminates spurious local minima, allowing gradient descent to find the low-rank solutions; (iii) the low-rank solution found using LoRA generalizes well.
Chat is not available.