Unverified50% confidenceFactExact time
Likelihood temperature scaling raises the likelihood function to the power of 1/T (T < 1), which is equivalent to multiplying the KL term in the ELBO by a coefficient T.
1
Sources
50%
Confidence
Long-term
Relevance
10/8/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedThe Softmax formula with temperature parameter T is P(xᵢ) = exp(zᵢ/T) / Σexp(zⱼ/T); when T→0 it degenerates to argmax, and when T→∞ it approaches a uniform distribution75% similarUnverified采样温度T=1时保持原始概率分布，T→0时输出趋于确定性，T>1时分布更平坦、输出更随机70% similarUnverifiedIn typical practice, the temperature parameter T is commonly set between 3 and 10; after distillation training is complete, the student model reverts to the standard T=1 setting at inference time.69% similarUnverifiedLuaJIT's hot loop and hot function thresholds can be adjusted via the -Ohotloop and -Ohotcall parameters.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/987032API
curl https://kongchang.com/api/v1/knowledge/claims/987032MCP
get_claim(id=987032)