Skip to yearly menu bar Skip to main content


Oral

LoRA Training in the NTK Regime has No Spurious Local Minima

Uijeong Jang · Jason Lee · Ernest Ryu

Hall A1
[ ] [ Visit Oral 6B Low Rank Learning ]
Thu 25 Jul 8:15 a.m. — 8:30 a.m. PDT
[ Slides

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.