Class Lars
java.lang.Object
ai.beestream.jitnn.nn.optim.Optimizer
ai.beestream.jitnn.nn.optim.Lars
LARS (You et al., 2017) with momentum: a per-parameter learning rate eta |p| / (|g| + weightDecay
|p|), applied to the decayed gradient and accumulated in a momentum buffer.
-
Field Summary
-
Constructor Summary
Constructors -
Method Summary
Methods inherited from class Optimizer
clipGradNorm, learningRate, loadScalars, loadStateDict, saveScalars, setLearningRate, stateDict, takeStats, zeroGrad
-
Constructor Details
-
Lars
-
-
Method Details
-
step
-
state
-