20260706:新增一些文章
This commit is contained in:
33
concepts/lottery-ticket-hypothesis.md
Normal file
33
concepts/lottery-ticket-hypothesis.md
Normal file
@@ -0,0 +1,33 @@
|
||||
---
|
||||
title: "Lottery Ticket Hypothesis: 稀疏子网络的彩票假说"
|
||||
created: 2026-06-25
|
||||
updated: 2026-06-25
|
||||
type: concept
|
||||
tags: [model-compression, pruning, sparse-networks]
|
||||
sources: ["[[sen-mapping-networks]]"]
|
||||
---
|
||||
|
||||
# Lottery Ticket Hypothesis (彩票假说)
|
||||
|
||||
Frankle & Carbin (2018) 提出的假说:**密集、随机初始化的前馈网络包含子网络("中奖彩票"),这些子网络在单独训练时能达到与原始网络相当的测试精度,且训练迭代次数相近**。
|
||||
|
||||
## 与 Mapping Networks 的关系
|
||||
|
||||
| 维度 | Lottery Ticket | Mapping Networks |
|
||||
|------|---------------|------------------|
|
||||
| 目标 | 找到稀疏子网络 | 学习低维参数生成映射 |
|
||||
| 阶段 | 后训练 / 迭代剪枝 | 训练时即嵌入 |
|
||||
| 理论基础 | 经验观察 | Mapping Theorem(存在性保证) |
|
||||
| 推理效率 | 提升(稀疏) | 不变(生成全参数) |
|
||||
| 训练效率 | 不变 | 大幅提升(200-500× 可训练参数减少) |
|
||||
|
||||
## 延伸
|
||||
|
||||
- **Linear Mode Connectivity**:SGD 解的 mode connectivity 支持参数空间存在结构
|
||||
- 可结合 Mapping Networks 的 Pruning 扩展同时降低训练和推理参数
|
||||
|
||||
## 参考
|
||||
|
||||
- Frankle & Carbin, "The Lottery Ticket Hypothesis", ICLR 2019
|
||||
- [[low-rank-decomposition]]
|
||||
- [[parameter-efficient-training]]
|
||||
Reference in New Issue
Block a user