2nd/10_Wiki/Topics/Domain_Programming/AI_and_ML/Loss-Functions-Foundations.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-loss-functions-foundations	Loss Functions Foundations	10_Wiki/Topics	verified	self	Loss Functions Cost Functions Objective Functions Loss-Functions	none	A	0.95	applied	loss objective training mse cross-entropy focal contrastive dice		2026-05-10	pending	language framework Python PyTorch

Loss Functions Foundations

매 한 줄

"매 loss는 task가 정한다". Regression→MSE/MAE/Huber, Classification→CE/Focal, Metric→Contrastive/Triplet, Segmentation→Dice/IoU.

매 핵심

매 회귀 (Regression)

• MSE (L2): ½(y-ŷ)². 미분 깔끔, outlier에 민감.
• MAE (L1): |y-ŷ|. robust, 0에서 미분 불가.
• Huber: |e|<δ면 MSE, 아니면 MAE. δ=1 기본.
• Log-cosh: smooth Huber. 자동 미분 친화.
• Quantile: max(τe, (τ-1)e). 중앙값/구간 예측.

매 분류 (Classification)

• BCE: -[y log p + (1-y) log(1-p)]. 이진/다중라벨.
• CE (softmax): -Σ y_k log p_k. 다중클래스.
• Focal (Lin 2017): -α(1-p)^γ log p. easy example down-weight, γ=2 기본.
• Label smoothing: y → y(1-ε) + ε/K. overconfidence 방지.
• Hinge: max(0, 1-y·ŷ). SVM. y∈{-1,+1}.

매 Metric Learning

• Contrastive (Hadsell 2006): pair. y·d² + (1-y)·max(0, m-d)².
• Triplet: max(0, d(a,p) - d(a,n) + margin).
• InfoNCE / NT-Xent (SimCLR): -log exp(sim+/τ) / Σ exp(sim/τ).
• Cosine embedding: 1 - cos(a,b).

매 Segmentation

• Dice: 1 - 2|A∩B|/(|A|+|B|). class imbalance 강함.
• IoU/Jaccard: 1 - |A∩B|/|A∪B|.
• Tversky: FP/FN weight 조정.
• Boundary loss: 거리변환 가중.

💻 패턴

Regression losses

import torch, torch.nn.functional as F
mse = F.mse_loss(pred, y)
mae = F.l1_loss(pred, y)
huber = F.huber_loss(pred, y, delta=1.0)        # smooth_l1 ≈ huber(δ=1)
# Quantile
def quantile_loss(pred, y, tau=0.5):
    e = y - pred
    return torch.maximum(tau*e, (tau-1)*e).mean()

Classification losses

ce = F.cross_entropy(logits, y_int)               # logits, not probs
bce = F.binary_cross_entropy_with_logits(logits, y_float)
# Label smoothing (built-in)
ce_ls = F.cross_entropy(logits, y_int, label_smoothing=0.1)

Focal loss (이진)

def focal_bce(logits, y, alpha=0.25, gamma=2.0):
    p = torch.sigmoid(logits)
    pt = torch.where(y == 1, p, 1 - p)
    alpha_t = torch.where(y == 1, alpha, 1 - alpha)
    return -(alpha_t * (1 - pt).pow(gamma) * pt.clamp_min(1e-8).log()).mean()

Triplet & InfoNCE

triplet = F.triplet_margin_loss(anchor, pos, neg, margin=1.0)

def info_nce(q, k_pos, k_neg, tau=0.07):
    # q: (B,D), k_pos: (B,D), k_neg: (B,N,D)
    pos = (q * k_pos).sum(-1, keepdim=True) / tau
    neg = torch.einsum("bd,bnd->bn", q, k_neg) / tau
    logits = torch.cat([pos, neg], dim=1)
    target = torch.zeros(q.size(0), dtype=torch.long, device=q.device)
    return F.cross_entropy(logits, target)

Dice + BCE (segmentation 표준)

def dice_loss(logits, y, eps=1e-6):
    p = torch.sigmoid(logits)
    inter = (p * y).sum(dim=(2, 3))
    union = p.sum(dim=(2, 3)) + y.sum(dim=(2, 3))
    return 1 - (2 * inter + eps) / (union + eps)

def combo_loss(logits, y):
    return 0.5 * F.binary_cross_entropy_with_logits(logits, y) + dice_loss(logits, y).mean()

Class imbalance 가중

weights = torch.tensor([1.0, 5.0, 2.0])           # 클래스별
ce_w = F.cross_entropy(logits, y_int, weight=weights)

매 결정 기준

Task	Default	변형
Regression normal	MSE	outlier→Huber, robust→MAE
Binary classification	BCE w/ logits	imbalance→Focal
Multi-class	CE w/ label smoothing	imbalance→class weights
Multi-label	BCE per-class
Embedding learning	InfoNCE	small batch→Triplet
Segmentation	BCE+Dice	small object→Tversky
Object detection	Focal + IoU/GIoU	(RetinaNet, YOLO)

기본값: classification CE+label smoothing 0.1, regression Huber.

🔗 Graph

• 부모: Optimization
• 변형: Focal-Loss
• 응용: Image-Classification-Mastery, Segmentation, Object-Detection
• Adjacent: Activation-Functions, Class-Imbalance, L1-and-L2-Regularization

🤖 LLM 활용

언제: task→loss 매핑, gradient 직관, 코드 템플릿 생성. 언제 X: domain-specific custom loss 설계는 검증 필수 (분포·gradient 분석).

❌ 안티패턴

• softmax 후 nll_loss 손수 (numerical) ← cross_entropy 사용
• BCE에 binary_cross_entropy(sigmoid(...)) ← _with_logits 사용
• Imbalance 무시한 CE
• Dice loss만 단독 (gradient 불안정) → BCE+Dice 혼합
• Focal γ를 imbalance 없을 때 사용 (성능↓)

🧪 검증 / 중복

• Verified (Goodfellow DL ch5, Lin 2017 Focal, SimCLR, Milletari V-Net Dice). 신뢰도 A.
• Canonical for Loss-Functions-Foundations (redirect).

🕓 Changelog

날짜	변경
2026-05-08	Phase 1
2026-05-10	Manual cleanup — canonical 강화, segmentation/metric 추가