---
id: wiki-2026-0508-kullback-leibler-divergence
title: Kullback-Leibler Divergence
category: 10_Wiki/Topics
status: verified
canonical_id: self
aliases: [KL Divergence, Relative Entropy, KL-D]
duplicate_of: none
source_trust_level: A
confidence_score: 0.95
verification_status: applied
tags: [information-theory, divergence, ml, vae, rlhf]
raw_sources: []
last_reinforced: 2026-05-10
github_commit: pending
tech_stack:
  language: python
  framework: torch, scipy
---

# Kullback-Leibler Divergence

## 매 한 줄
> **"매 distribution 간의 directed information loss"**. KL Divergence $D_{\text{KL}}(P \| Q) = \mathbb{E}_P[\log P/Q]$ 는 reference distribution $Q$ 로 $P$ 를 encode 시 expected extra bits. Kullback & Leibler (1951) 가 정의했고, 2026 ML 에서는 VAE ELBO, RLHF (PPO/DPO), variational inference, distillation 의 매 core loss term.

## 매 핵심

### 매 Definition
- discrete: $D_{\text{KL}}(P\|Q) = \sum_x P(x) \log \frac{P(x)}{Q(x)}$
- continuous: $\int p(x) \log \frac{p(x)}{q(x)} dx$
- always $\ge 0$ (Gibbs inequality), $=0$ iff $P=Q$
- **NOT symmetric**, **NOT a metric** (no triangle inequality)
- $D_{\text{KL}}(P\|Q) = H(P, Q) - H(P)$ — cross-entropy minus entropy

### 매 Mode behavior
- **Forward $D_{\text{KL}}(P\|Q)$**: Q must cover all mass of P → "mode-covering"
- **Reverse $D_{\text{KL}}(Q\|P)$**: Q goes where P has mass → "mode-seeking"
- VAE 는 reverse, EP 는 forward

### 매 응용
1. **VAE ELBO**: $\mathbb{E}[\log p(x|z)] - D_{\text{KL}}(q(z|x) \| p(z))$.
2. **RLHF PPO**: $\beta \cdot D_{\text{KL}}(\pi \| \pi_{\text{ref}})$ penalty.
3. **Knowledge distillation**: $D_{\text{KL}}(p_T \| p_S)$ with temperature.
4. **Variational inference**: $\arg\min_q D_{\text{KL}}(q \| p)$.
5. **Mutual information**: $I(X;Y) = D_{\text{KL}}(p(x,y) \| p(x)p(y))$.

## 💻 패턴

### Discrete KL
```python
import numpy as np
def kl_div(p, q, eps=1e-12):
    p, q = np.asarray(p), np.asarray(q)
    return np.sum(p * (np.log(p + eps) - np.log(q + eps)))

p = np.array([0.5, 0.3, 0.2])
q = np.array([0.4, 0.4, 0.2])
print(kl_div(p, q))
```

### PyTorch KL (numerically stable)
```python
import torch
import torch.nn.functional as F

# inputs MUST be log-probs for kl_div first arg
log_p = F.log_softmax(model_logits, dim=-1)
q = F.softmax(target_logits, dim=-1)
loss = F.kl_div(log_p, q, reduction="batchmean")
```

### KL between Gaussians (closed form)
```python
def kl_gaussian(mu1, var1, mu2, var2):
    return 0.5 * (
        torch.log(var2 / var1) + (var1 + (mu1-mu2)**2) / var2 - 1
    ).sum()

# VAE: q ~ N(mu, sigma^2), prior N(0, 1)
def kl_to_standard_normal(mu, log_var):
    return -0.5 * torch.sum(1 + log_var - mu.pow(2) - log_var.exp())
```

### Distillation loss with temperature
```python
def distill_kl(student_logits, teacher_logits, T=4.0):
    log_p_s = F.log_softmax(student_logits / T, dim=-1)
    p_t = F.softmax(teacher_logits / T, dim=-1)
    return F.kl_div(log_p_s, p_t, reduction="batchmean") * (T*T)
```

### RLHF PPO KL penalty (per-token)
```python
def ppo_kl_penalty(logp_new, logp_ref, beta=0.05):
    # token-level KL via log-prob difference
    return beta * (logp_new - logp_ref)  # used as reward shaping
```

### Forward vs reverse comparison
```python
# Approximate q (Gaussian) to bimodal p
# - reverse KL D(q||p): q picks one mode (mode-seeking)
# - forward KL D(p||q): q spans both modes (mode-covering, broader)
```

## 매 결정 기준
| Need | Form |
|---|---|
| variational posterior fit | reverse $D_{\text{KL}}(q\|p)$ |
| spread (cover all modes) | forward $D_{\text{KL}}(p\|q)$ |
| symmetric | JS divergence |
| bounded, metric | Wasserstein, Hellinger |
| RLHF stability | per-token reverse KL with $\beta$ schedule |

**기본값**: 매 problem 따라 — VAE 면 reverse, EP 면 forward.

## 🔗 Graph
- 부모: [[Information_Theory|Information-Theory]]
- 응용: [[VAE]] · [[RLHF]] · [[LLM_Optimization_and_Deployment_Strategies|Knowledge-Distillation]] · [[Variational-Inference]]
- Adjacent: [[Cross-Entropy]] · [[Mutual-Information]]

## 🤖 LLM 활용
**언제**: 매 distribution-level loss 정의, RLHF 의 reference model anchoring, distillation.
**언제 X**: 매 distance metric 이 필요할 때 — KL 은 metric 이 X — Wasserstein 사용.

## ❌ 안티패턴
- **Symmetric 가정**: $D_{\text{KL}}(P\|Q) \ne D_{\text{KL}}(Q\|P)$.
- **Disjoint support**: $Q(x)=0, P(x)>0$ 이면 $\infty$ — smooth or use JS.
- **`F.kl_div` 의 input 순서 혼동**: 첫 arg 는 log-prob.
- **Distillation T 무시**: temperature $T$ 없이 sharp distribution 사용 → poor signal.
- **RLHF 에서 KL collapse**: $\beta$ 너무 작으면 reward hacking.

## 🧪 검증 / 중복
- Verified (Cover & Thomas 2006 textbook ch 2, MacKay 2003 ch 2, Kingma VAE 2013).
- 신뢰도 A.

## 🕓 Changelog
| 날짜 | 변경 |
|---|---|
| 2026-05-08 | Phase 1 |
| 2026-05-10 | Manual cleanup — KL definition, mode behavior, VAE/RLHF/distillation patterns |