20260518-morning:新增内容
This commit is contained in:
29
concepts/zero-cost-proxies.md
Normal file
29
concepts/zero-cost-proxies.md
Normal file
@@ -0,0 +1,29 @@
|
||||
---
|
||||
title: "Zero-Cost Proxies (ZCP)"
|
||||
created: 2026-05-15
|
||||
updated: 2026-05-15
|
||||
type: concept
|
||||
tags: [machine-learning, neural-architecture-search, efficiency]
|
||||
sources: [raw/papers/zeng-neurida-2025.md]
|
||||
---
|
||||
|
||||
# Zero-Cost Proxies (ZCP)
|
||||
|
||||
**Zero-Cost Proxies** 是源自 Neural Architecture Search (NAS) 的技术,在**不进行完整训练的情况下**估计模型在给定任务上的性能。
|
||||
|
||||
## 核心思想
|
||||
|
||||
在模型初始化阶段通过某些可计算的代用指标(如梯度范数、激活模式、雅可比矩阵特征等)来预测模型的最终性能,成本接近零(无需梯度下降迭代)。
|
||||
|
||||
## 在 NeurIDA 中的应用
|
||||
|
||||
[[conditional-model-dispatcher|Conditional Model Dispatcher]] 使用 ZCP 对 [[composable-base-model-architecture|基础模型池]] 中每个候选模型进行快速评分,实现轻量级的模型选择。ZCP 评分的低成本意味着 Dispatcher 可以在几乎不增加延迟的情况下完成模型选择决策。
|
||||
|
||||
## 关键参考文献
|
||||
|
||||
- Abdelfattah et al., "Zero-Cost Proxies for Lightweight NAS", ICLR 2021
|
||||
- Shu et al., "NASI: Label- and Data-agnostic Neural Architecture Search at Initialization", ICLR 2022
|
||||
|
||||
## 来源
|
||||
|
||||
- [[zeng-neurida-2025|NeurIDA 论文]]
|
||||
Reference in New Issue
Block a user