20260601
This commit is contained in:
39
concepts/inference-time-scaling.md
Normal file
39
concepts/inference-time-scaling.md
Normal file
@@ -0,0 +1,39 @@
|
||||
---
|
||||
title: "Inference-Time Scaling(推理时扩展)"
|
||||
created: 2026-05-23
|
||||
updated: 2026-05-23
|
||||
type: concept
|
||||
tags: [inference, scaling, reasoning, compute]
|
||||
sources: [raw/papers/gram-generative-recursive-reasoning-2026.md]
|
||||
confidence: high
|
||||
---
|
||||
|
||||
# Inference-Time Scaling
|
||||
|
||||
> GRAM 提出的双维度推理扩展:不仅通过**递归深度**(deeper),还通过**并行轨迹采样数**(wider)来提升推理质量。
|
||||
|
||||
## 两种扩展维度
|
||||
|
||||
| 维度 | 方式 | 效果 |
|
||||
|------|------|------|
|
||||
| **深度** (Deep) | 增加递归步数 T | 更多精炼迭代 |
|
||||
| **宽度** (Wide) | 并行采样更多轨迹 | 更好的边际化估计、多解发现 |
|
||||
|
||||
## 与传统扩展方式的区别
|
||||
|
||||
- **Chain-of-Thought**: 只能 depth(更长 token 序列)
|
||||
- **Ensemble**: 只能 width(多个独立模型)
|
||||
- **GRAM**: **depth x width**(单一模型的递归深度 x 轨迹数)
|
||||
|
||||
## 关键洞察
|
||||
|
||||
深度和宽度的边际收益不同:
|
||||
- 深度对单解精炼最有效
|
||||
- 宽度对多解覆盖和不确定性处理最有效
|
||||
- 最优配置 = 任务依赖的资源分配
|
||||
|
||||
## 相关概念
|
||||
|
||||
- [[width-based-scaling]]
|
||||
- [[deep-and-wide-reasoning]]
|
||||
- [[gram-generative-recursive-reasoning|GRAM]]
|
||||
Reference in New Issue
Block a user