Statements (21)
Predicate | Object |
---|---|
gptkbp:instanceOf |
mathematical optimization
|
gptkbp:advantage |
handles sparse data well
|
gptkbp:alsoKnownAs |
gptkb:AdaGrad
|
gptkbp:feature |
adapts learning rate for each parameter
|
https://www.w3.org/2000/01/rdf-schema#label |
Adaptive Gradient Algorithm
|
gptkbp:limitation |
learning rate decays too aggressively
|
gptkbp:mainActivity |
deep learning
stochastic optimization convex optimization |
gptkbp:proposedBy |
gptkb:Yoram_Singer
gptkb:Elad_Hazan gptkb:John_Duchi 2011 |
gptkbp:publishedIn |
gptkb:Journal_of_Machine_Learning_Research
|
gptkbp:relatedTo |
gptkb:Adam
gptkb:RMSProp gradient descent |
gptkbp:url |
https://jmlr.org/papers/volume12/duchi11a/duchi11a.pdf
|
gptkbp:usedIn |
gptkb:machine_learning
|
gptkbp:bfsParent |
gptkb:AdaGrad
|
gptkbp:bfsLayer |
6
|