20260601
This commit is contained in:
32
concepts/amortized-variational-inference.md
Normal file
32
concepts/amortized-variational-inference.md
Normal file
@@ -0,0 +1,32 @@
|
||||
---
|
||||
title: "Amortized Variational Inference(摊销变分推断)"
|
||||
created: 2026-05-23
|
||||
updated: 2026-05-23
|
||||
type: concept
|
||||
tags: [training, variational-inference, probabilistic, vae]
|
||||
sources: [raw/papers/gram-generative-recursive-reasoning-2026.md]
|
||||
confidence: medium
|
||||
---
|
||||
|
||||
# Amortized Variational Inference
|
||||
|
||||
> GRAM 的训练方法:使用编码器(后验)和生成器(先验)来优化 ELBO,CE loss 驱动预测 + KL divergence 规范潜在空间。
|
||||
|
||||
## GRAM 中的实现
|
||||
|
||||
- **后验 q_phi(z_t | z_{t-1}, y)**:知道答案时的推理轨迹
|
||||
- **先验 p_theta(z_t | z_{t-1}, e_x)**:不知道答案时的推理轨迹
|
||||
- **训练目标**: ELBO = E_q[log p(y|z_T)] - KL(q||p)
|
||||
- **CE loss**: 确保预测正确
|
||||
- **KL divergence**: 确保模型在没有答案时也能产生合理轨迹
|
||||
|
||||
## 为什么用摊销变分推断
|
||||
|
||||
- 直接最大化似然 intractable(需要边缘化所有轨迹)
|
||||
- VI 提供了可微分的训练信号
|
||||
- 后验网络在训练时提供"老师"信号,测试时只用先验
|
||||
|
||||
## 相关概念
|
||||
|
||||
- [[latent-variable-generative-model]]
|
||||
- [[gram-generative-recursive-reasoning|GRAM]]
|
||||
Reference in New Issue
Block a user