2nd/10_Wiki/Topic_Programming/AI_and_ML/Exploding-Gradient Problem.md

id, title, category, status, canonical_id, aliases, duplicate_of, source_trust_level, confidence_score, verification_status, tags, raw_sources, last_reinforced, github_commit, tech_stack

id	title	category	status	canonical_id	aliases	duplicate_of	source_trust_level	confidence_score	verification_status	tags	raw_sources	last_reinforced	github_commit	tech_stack
wiki-2026-0508-exploding-gradient-problem	Exploding Gradient Problem	10_Wiki/Topics	verified	self	exploding gradient gradient clipping RNN explosion weight init Xavier He	none	A	0.98	applied	deep-learning training gradient-explosion gradient-clipping weight-initialization		2026-05-10	pending	language framework Python PyTorch / TensorFlow

Exploding Gradient Problem

매 한 줄

"매 deep / recurrent network 의 gradient 의 magnitude 의 explode". 매 loss = NaN. 매 cause: 매 deep chain rule + 매 weight > 1 의 multiply. 매 mitigation: gradient clipping, 매 better init (Xavier/He), 매 LayerNorm, 매 residual.

매 핵심

매 cause

• Chain rule: 매 ∏ (∂h/∂h_prev) > 1 → exp.
• RNN: 매 same weight 의 매 timestep multiply.
• Bad init: 매 weight scale.
• High learning rate.
• No normalization.

매 detection

• Loss = NaN.
• Grad norm = inf.
• Weight diverge.
• Activation overflow.

매 mitigation

1. Gradient clipping (norm or value).
2. Weight init (Xavier, He, orthogonal).
3. LayerNorm / BatchNorm.
4. Residual connection.
5. LSTM / GRU (gating).
6. Smaller learning rate.
7. Gradient check.

매 응용

• RNN / LSTM training.
• Deep Transformer.
• GAN training.
• RL policy.

💻 패턴

Gradient clipping (norm)

import torch
def train_step(model, loss, optim, max_norm=1.0):
    optim.zero_grad()
    loss.backward()
    torch.nn.utils.clip_grad_norm_(model.parameters(), max_norm)
    optim.step()

Gradient clipping (value)

torch.nn.utils.clip_grad_value_(model.parameters(), clip_value=0.5)

Adaptive clip (recent)

def adaptive_clip(grads, percentile=99):
    norms = [g.norm() for g in grads]
    threshold = np.percentile([n.item() for n in norms], percentile)
    for g in grads: g.data.mul_(min(1, threshold / max(g.norm(), 1e-6)))

Xavier / Glorot init

import torch.nn as nn
for m in model.modules():
    if isinstance(m, nn.Linear):
        nn.init.xavier_uniform_(m.weight)
        nn.init.zeros_(m.bias)

He init (ReLU)

for m in model.modules():
    if isinstance(m, nn.Linear):
        nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')

Orthogonal init (RNN)

for name, param in model.named_parameters():
    if 'weight_hh' in name:
        nn.init.orthogonal_(param)

LayerNorm

class TransformerBlock(nn.Module):
    def __init__(self, d):
        super().__init__()
        self.ln1 = nn.LayerNorm(d)
        self.ln2 = nn.LayerNorm(d)
        self.attn = MultiHeadAttention(d)
        self.mlp = nn.Sequential(nn.Linear(d, 4*d), nn.GELU(), nn.Linear(4*d, d))
    
    def forward(self, x):
        x = x + self.attn(self.ln1(x))  # 매 pre-norm
        x = x + self.mlp(self.ln2(x))
        return x

Residual connection

class ResBlock(nn.Module):
    def __init__(self, d):
        super().__init__()
        self.layers = nn.Sequential(nn.Linear(d, d), nn.ReLU(), nn.Linear(d, d))
    
    def forward(self, x):
        return x + self.layers(x)  # 매 gradient highway

Detect explosion (logging)

def grad_norm(model):
    total = 0
    for p in model.parameters():
        if p.grad is not None: total += p.grad.norm().item() ** 2
    return total ** 0.5

# 매 monitor + alert
gn = grad_norm(model)
if gn > 100 or np.isnan(gn):
    print(f'⚠️ Grad norm: {gn}')

NaN guard

def safe_train_step(model, loss, optim):
    if torch.isnan(loss).any() or torch.isinf(loss).any():
        print('Skipping NaN/Inf loss')
        return
    optim.zero_grad()
    loss.backward()
    grad_ok = all(not torch.isnan(p.grad).any() for p in model.parameters() if p.grad is not None)
    if grad_ok: optim.step()

LR warmup (transformer)

def warmup_cosine(step, warmup=4000, total=100000, peak_lr=1e-4):
    if step < warmup: return peak_lr * step / warmup
    progress = (step - warmup) / (total - warmup)
    return peak_lr * 0.5 * (1 + np.cos(np.pi * progress))

Mixed precision (with GradScaler)

from torch.cuda.amp import autocast, GradScaler
scaler = GradScaler()

with autocast():
    loss = model(batch)

scaler.scale(loss).backward()
scaler.unscale_(optim)
torch.nn.utils.clip_grad_norm_(model.parameters(), 1.0)
scaler.step(optim)
scaler.update()

LSTM (gating fix for RNN)

self.lstm = nn.LSTM(input_size, hidden_size, num_layers=2, batch_first=True)
# 매 forget gate 의 의 의 long sequence stabilize

TBPTT (truncated BPTT)

def tbptt_train(model, sequence, chunk=20):
    h = None
    losses = []
    for i in range(0, len(sequence), chunk):
        chunk_data = sequence[i:i+chunk]
        out, h = model(chunk_data, h)
        h = (h[0].detach(), h[1].detach())  # 매 detach 의 backprop 의 limit
        loss = compute_loss(out, target)
        loss.backward()
        torch.nn.utils.clip_grad_norm_(model.parameters(), 1.0)
        optim.step(); optim.zero_grad()
        losses.append(loss.item())
    return losses

매 결정 기준

상황	Mitigation
Default DL	Clip + LayerNorm + He init
RNN	+ orthogonal + TBPTT
Transformer	LayerNorm + warmup
GAN	Spectral norm + low LR
Mixed precision	+ GradScaler

기본값: 매 grad clip 1.0 + 매 He init + 매 LayerNorm + 매 LR warmup + 매 NaN guard.

🔗 Graph

• 부모: Deep Learning · Optimization
• 변형: Gradient-Clipping
• 응용: 데이터 사이언스 및 ML 엔지니어링 · Transformer · Generative-Adversarial-Networks
• Adjacent: LayerNorm

🤖 LLM 활용

언제: 매 deep model train. 매 RNN. 매 GAN. 언제 X: 매 shallow / pretrained inference.

❌ 안티패턴

• No clip in RNN: 매 NaN guarantee.
• Default init in deep ReLU: 매 He init 의 use.
• No LR warmup: 매 transformer fail.
• Ignore NaN once: 매 cascade.
• Clip 너무 작게: 매 underfit.

🧪 검증 / 중복

• Verified (Pascanu 2013, He init 2015, Goodfellow Deep Learning).
• 신뢰도 A.

🕓 Changelog

날짜	변경
2026-04-26	GRAD-EXPL auto
2026-05-08	Phase 1
2026-05-10	Manual cleanup — clip / init / norm / TBPTT / mixed-prec code