20260601
This commit is contained in:
46
concepts/bayesian-wind-tunnels.md
Normal file
46
concepts/bayesian-wind-tunnels.md
Normal file
@@ -0,0 +1,46 @@
|
||||
---
|
||||
title: "Bayesian Wind Tunnels"
|
||||
created: 2026-05-26
|
||||
type: concept
|
||||
tags: ["bayesian-inference", "experimental-methodology", "transformers"]
|
||||
sources: ["agarwal-bayesian-attention-geometry"]
|
||||
---
|
||||
|
||||
# Bayesian Wind Tunnels
|
||||
|
||||
> 受控预测环境:解析后验已知、记忆不可行、推理必须为真——用于可验证地测试神经序列模型是否实现贝叶斯推理。
|
||||
|
||||
## 三个条件
|
||||
|
||||
1. **解析后验已知**:每一步的真值 posterior 在闭合形式中精确已知
|
||||
2. **记忆不可行**:假设空间太大(如双射数量为 n!),计算上无法记忆
|
||||
3. **推理必要性**:in-context prediction 需要真正的概率推理
|
||||
|
||||
## 解决的问题
|
||||
|
||||
自然语言评测的致命缺陷:
|
||||
- 没有 ground-truth posterior
|
||||
- 大模型无法隔离记忆与推理
|
||||
- 只能观察行为,不能验证内部计算
|
||||
|
||||
Wind tunnel 将定性问题("它在做贝叶斯吗?")转化为定量测试:**模型的预测熵是否与解析 posterior 熵逐位置匹配?**
|
||||
|
||||
## 四种 Wind Tunnel 任务
|
||||
|
||||
| 任务 | 类型 | 测试原语 |
|
||||
|------|------|---------|
|
||||
| 双射学习 (Bijection Learning) | 离散假设消除 | [[belief-accumulation]] |
|
||||
| HMM 滤波 | 序列随机推理 | 累积 + [[belief-transport]] |
|
||||
| 贝叶斯回归 | 连续推理 | 累积 |
|
||||
| 联想回忆 (Associative Recall) | 基于内容的检索 | [[random-access-binding]] |
|
||||
|
||||
## 与风洞的类比
|
||||
|
||||
航空风洞:控制气流、测量升力/阻力、验证空气动力学理论。
|
||||
Bayesian wind tunnel:控制概率环境、测量预测熵、验证[[inference-primitives|推理原语]]理论。
|
||||
|
||||
## 相关页面
|
||||
|
||||
- [[inference-primitives]] — 被 wind tunnel 验证的原语体系
|
||||
- [[bayesian-attention-geometry]] — wind tunnel 中发现的几何结构
|
||||
- [[agarwal-bayesian-attention-geometry]] — 原始论文
|
||||
Reference in New Issue
Block a user