Adam
E701496
Adam is a popular stochastic optimization algorithm widely used to train deep learning models by adaptively adjusting learning rates for each parameter.
All labels observed (1)
| Label | Occurrences |
|---|---|
| Adam canonical | 2 |
How this entity was disambiguated
This entity first appeared as the object of triple T7874748 — resolving that mention is where its identity was fixed. The disambiguator weighed these candidate entities and picked the highlighted one (or “None”, minting a new entity). This is how homonymy is resolved: the same surface form can point to different entities.
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Adam Context triple: [Adam: A Method for Stochastic Optimization, shortTitle, Adam]
-
A.
Adam
Adam is the first human in Abrahamic religious traditions, whose disobedience in Eden is believed to have introduced sin into the human condition.
-
B.
Adam
Adam is a common surname of Scottish and English origin, borne by various notable individuals including architects, politicians, and artists.
-
C.
Adam
Adam is a loyal, elderly servant in William Shakespeare’s comedy "As You Like It," known for his devotion and generosity toward Orlando.
-
D.
Adam
"Adam" is a 1983 American television film based on the true story of the kidnapping and murder of Adam Walsh, in which JoBeth Williams stars as the boy’s mother.
-
E.
Adam
Adam is a reclusive, centuries-old vampire musician and one of the two melancholic immortal lovers at the center of Jim Jarmusch’s film "Only Lovers Left Alive."
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Adam Target entity description: Adam is a popular stochastic optimization algorithm widely used to train deep learning models by adaptively adjusting learning rates for each parameter.
-
A.
Adam
Adam is a masculine given name of Hebrew origin, commonly used in many cultures and languages.
-
B.
Adam
Adam is a renowned sculpture by Auguste Rodin, notable for its expressive depiction of the biblical figure and housed in the Rodin Museum.
-
C.
Adam
Adam is a common surname of Scottish and English origin, borne by various notable individuals including architects, politicians, and artists.
-
D.
Adam
Adam is the first human in Abrahamic religious traditions, whose disobedience in Eden is believed to have introduced sin into the human condition.
-
E.
Adam
Adam is a reclusive, centuries-old vampire musician and one of the two melancholic immortal lovers at the center of Jim Jarmusch’s film "Only Lovers Left Alive."
- F. None of above. chosen
Statements (50)
| Predicate | Object |
|---|---|
| instanceOf |
gradient-based optimization algorithm
ⓘ
optimization algorithm ⓘ stochastic optimization method ⓘ |
| advantage |
computationally efficient
ⓘ
invariant to diagonal rescaling of gradients ⓘ requires little hyperparameter tuning ⓘ works well with sparse gradients ⓘ |
| basedOn |
adaptive learning rate methods
ⓘ
momentum methods ⓘ stochastic gradient descent ⓘ |
| category | first-order optimization algorithm ⓘ |
| combinesIdeaOf |
RMSProp
ⓘ
momentum ⓘ |
| commonlyUsedIn |
computer vision models
ⓘ
natural language processing models ⓘ reinforcement learning ⓘ |
| defaultBeta1 | 0.9 ⓘ |
| defaultBeta2 | 0.999 ⓘ |
| defaultEpsilon | 1e-8 ⓘ |
| defaultLearningRate | 0.001 ⓘ |
| field |
deep learning
ⓘ
machine learning ⓘ |
| fullName |
Adaptive Moment Estimation
ⓘ
linked to:
Adam: A Method for Stochastic Optimization
|
| hasHyperparameter |
beta1
ⓘ
beta2 ⓘ epsilon ⓘ learning rate ⓘ |
| hasVariant |
AMSGrad
ⓘ
AdaBound ⓘ AdamW ⓘ
linked to:
Adam optimizer
|
| implementedIn |
JAX
ⓘ
Keras ⓘ PyTorch ⓘ TensorFlow ⓘ |
| introducedBy |
Diederik P. Kingma
ⓘ
Jimmy Ba ⓘ |
| introducedInPaper | Adam: A Method for Stochastic Optimization ⓘ |
| limitation |
can converge to different minima than SGD
ⓘ
may generalize worse than SGD with momentum in some settings ⓘ |
| maintains |
exponential moving average of gradients
ⓘ
exponential moving average of squared gradients ⓘ |
| property |
adaptive learning rate per parameter
ⓘ
bias-corrected first moment estimates ⓘ bias-corrected second moment estimates ⓘ |
| publicationVenue |
International Conference on Learning Representations
ⓘ
linked to:
ICLR
|
| publicationYear | 2014 ⓘ |
| usedFor |
minimizing loss functions
ⓘ
neural network training ⓘ stochastic optimization ⓘ training deep learning models ⓘ |
How these facts were elicited
The pipeline generated the facts above by prompting gpt-5.1 with this entity's name + description and the instruction below.
Instruction
You are a knowledge base construction expert. Given a subject entity and a description of it, return factual statements that you know for the subject as a JSON list of dictionaries(triples), where keys must be "subject", "predicate" and "object". The number of facts may be very high, between 25 to 50 or more, for very popular subjects. For less popular subjects, the number of facts can be very low, like 5 or 10. # Requirements - If you don't know the subject at all, return an empty list. - If the subject is not a named entity, return an empty list. - Include at least one triple where predicate is "instanceOf". - Do not get too wordy. - Separate several objects into multiple triples with one object.
Input
Subject: Adam Description of subject: Adam is a popular stochastic optimization algorithm widely used to train deep learning models by adaptively adjusting learning rates for each parameter.
Referenced by (2)
Full triples — surface form annotated when it differs from this entity's canonical label.