Files
myWiki/concepts/lora.md

39 lines
1.2 KiB
Markdown
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

---
title: "LoRA (Low-Rank Adaptation)"
created: 2026-06-01
updated: 2026-06-01
type: concept
tags: [fine-tuning, peft, llm]
sources: [raw/papers/xu-why-steering-works-2026.md]
confidence: medium
---
# LoRA低秩适配
## 定义
LoRALow-Rank Adaptation, Hu et al., 2022是一种参数高效微调方法通过冻结原始权重 $W$ 并训练低秩更新 $\Delta W = BA$$B \in \mathbb{R}^{d \times r}, A \in \mathbb{R}^{r \times k}, r \ll \min(d,k)$)来适配模型。
推理时:$W \leftarrow W + \Delta W = W + BA$
## 在统一动态权重视角中
在 Xu et al. (2026) 的统一框架中,带缩放系数的 LoRA 表达为:
$$h_{i+1} = (W + mBA)h_i + b$$
$$\Delta h = m(BA h_i)$$
LoRA 是**仅修改 W**(不修改 b的动态权重更新参数规模为 $d_{in} \times r + r \times d_{out}$。
## 导向动态
LoRA 与其他干预形式一样呈现三阶段偏好动态和效用衰减,其表现与 Local Weight 方法高度一致。
## 相关概念
- [[dynamic-weight-updates]] — 统一框架中的 LoRA 位置
- [[activation-steering]] — b-only 的动态更新
- [[steering-dynamics]] — LoRA 的偏好-效用动态
- [[xu-why-steering-works]] — 源论文