Class FedYogiServerOptimizer<T>

Namespace

AiDotNet.FederatedLearning.ServerOptimizers

Assembly

AiDotNet.dll

FedYogi server optimizer.

public sealed class FedYogiServerOptimizer<T> : FederatedServerOptimizerBase<T>, IFederatedServerOptimizer<T>

Type Parameters

T

Inheritance

object

FederatedLearningComponentBase<T>

FederatedServerOptimizerBase<T>

FedYogiServerOptimizer<T>

Implements

IFederatedServerOptimizer<T>

Inherited Members

object.Equals(object)

object.Equals(object, object)

object.GetHashCode()

object.GetType()

object.ReferenceEquals(object, object)

object.ToString()

Remarks

For Beginners: Yogi is similar to Adam, but it can be more stable when updates are noisy or sparse.

Constructors

FedYogiServerOptimizer(double, double, double, double)

public FedYogiServerOptimizer(double learningRate = 1, double beta1 = 0.9, double beta2 = 0.999, double epsilon = 1E-08)

Parameters

learningRate double

beta1 double

beta2 double

epsilon double

Methods

GetOptimizerName()

Gets the name of the server optimizer.

public override string GetOptimizerName()

Returns

string

Step(Vector<T>, Vector<T>)

Updates global parameters given the current parameters and an aggregated target.

public override Vector<T> Step(Vector<T> currentGlobalParameters, Vector<T> aggregatedTargetParameters)

Parameters

currentGlobalParameters Vector<T>

The current global parameter vector.

aggregatedTargetParameters Vector<T>

The aggregated target parameter vector (e.g., FedAvg output).

Returns

Vector<T>

The updated global parameter vector.