Class Adagrad

Adagrad is an optimizer with parameter-specific learning rates, which are adapted relative to how frequently a parameter gets updated during training. The more updates a parameter receives, the smaller the learning rate.

Inheritance

System.Object

BaseOptimizer

Adagrad

Inherited Members

BaseOptimizer.Name

BaseOptimizer.LearningRate

BaseOptimizer.Momentum

BaseOptimizer.DecayRate

Namespace: SiaNet.Optimizers

Assembly: SiaNet.dll

Syntax

public class Adagrad : BaseOptimizer

Constructors

Adagrad(Single, Single, Single)

Initializes a new instance of the Adagrad class.

Declaration

public Adagrad(float lr = 0.01F, float decayRate = 0F, float epsilon = 1E-07F)

Parameters

Type	Name	Description
System.Single	lr	Initial learning rate for the optimizer.
System.Single	decayRate	Learning rate decay over each update.
System.Single	epsilon	Fuzz factor. Lowest float value but > 0

Properties

Epsilon

Fuzz factor. Lowest float value but > 0

Declaration

public float Epsilon { get; set; }

Property Value

Type	Description
System.Single	The epsilon.

See Also

BaseOptimizer