Adagrad class

Implements the Adagrad optimizer.

Adagrad is an adaptive learning rate optimizer that provides individual learning rates for each parameter. It adapts the rates by dividing by the square root of the sum of all past squared gradients.

This makes it particularly well-suited for sparse data (like word embeddings), as parameters that are updated infrequently will receive larger updates.

Example

Optimizer optimizer = Adagrad(model.parameters, learningRate: 0.01);
Inheritance

Constructors

Adagrad(List<Tensor> parameters, {required double learningRate, double epsilon = 1e-8})

Properties

epsilon double
final
hashCode int
The hash code for this object.
no setterinherited
learningRate double
The step size for the gradient updates.
finalinherited
parameters List<Tensor>
The list of model parameters (weights and biases) that this optimizer will update.
finalinherited
runtimeType Type
A representation of the runtime type of the object.
no setterinherited

Methods

noSuchMethod(Invocation invocation) → dynamic
Invoked when a nonexistent method or property is accessed.
inherited
step() → void
Performs a single optimization step according to the Adagrad update rule.
override
toString() String
A string representation of this object.
inherited
zeroGrad() → void
Resets the gradients of all parameters to zero.
inherited

Operators

operator ==(Object other) bool
The equality operator.
inherited