Files
myWiki/concepts/real-log-canonical-threshold.md

53 lines
1.6 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: "实对数典范阈值 (Real Log Canonical Threshold, RLCT)"
created: 2026-06-10
updated: 2026-06-10
type: concept
tags: ["singular-learning-theory", "bayesian-statistics", "algebraic-geometry"]
sources: ["[[dead-directions-geometric-singular-learning]]"]
---
# 实对数典范阈值 (RLCT, lambda)
**RLCT** 是 [[singular-learning-theory|Watanabe 奇异学习理论]]中主导贝叶斯自由能渐近修正的不变量:
```
F_n = n · S_n + lambda · log n + (m-1) · log log n + O(1)
```
- n: 样本量
- S_n: 经验熵
- **lambda**:实对数典范阈值
- m重数multiplicity
## 几何含义
lambda 是有理数(广中平祐定理的推论),反映奇异集在参数空间中的"尖锐程度"
- lambda 小 → 奇异集尖锐 → 模型复杂度低 → 更好的泛化
- lambda 大 → 奇异集平坦 → 模型复杂度高
## 与 Dead Direction 的关系
[[dead-directions-geometric-singular-learning|Shirodkar (2026)]] 的核心贡献:对于单 dead direction
```
lambda = 1/(2k)
```
其中 k 是 [[kl-order|KL 阶]],可从 Fisher 曲率衰减率计算——在原始坐标中,无需消解。
## 传统计算方式
需要通过广中平祐消解Hironaka resolution将奇异集"吹开"——对百万参数网络不可行。Shirodkar 的贡献使 lambda 在原始坐标中可计算。
## 与其他不变量
[[watanabe-triple|Watanabe 三元组]] (lambda, m, nu) 完整刻画了奇异模型的贝叶斯渐近性质。
## 参考
- [[dead-directions-geometric-singular-learning|Dead Directions]]
- [[singular-learning-theory|Singular Learning Theory]]
- [[watanabe-triple|Watanabe's Triple]]
- [[kl-order|KL Order]]