Unverified90% confidenceFactTime unknown
Adam在RMSProp基础上进一步引入一阶矩（动量），并增加了偏差修正机制
1
Sources
90%
Confidence
Long-term
Relevance
5/31/2026
First Seen
Sources
Adam优化器深度拆解：一文搞懂自适应矩估计原理
bilibili深度学习自习室
Related Entities
Related Claims
VerifiedAdam combines the momentum method with RMSprop's adaptive learning rate, independently maintaining exponential moving averages of the first-order and second-order gradients for each parameter.75% similarVerifiedThe Adam optimizer combines the advantages of Momentum and RMSProp, maintaining exponential moving averages of the first-order moment estimate and second-order moment estimate of the gradients.72% similarUnverifiedThe Adam optimizer was proposed by Diederik Kingma and Jimmy Ba in 2014 and requires maintaining two sets of state: first-order momentum and second-order momentum.63% similarUnverifiedAdamW引入权重衰减解耦，Lion基于符号动量且显存更低62% similarUnverified梯度下降及其变体（Adam、AdaGrad等）本质上是数值优化算法60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/7722API
curl https://kongchang.com/api/v1/knowledge/claims/7722MCP
get_claim(id=7722)