Package ai.djl.training.optimizer

Class Adagrad

java.lang.Object

ai.djl.training.optimizer.Optimizer

ai.djl.training.optimizer.Adagrad

public class Adagrad
extends Optimizer

Adagrad is an AdaGrad Optimizer.

This class implements

Adagrad updates the weights using:

\( grad = clip(grad * resc_grad, clip_grad) + wd * weight \)
\( history += grad^2 \)
\( weight -= lr * grad / (sqrt(history) + epsilon) \)

where grad represents the gradient, wd represents weight decay, and lr represents learning rate.

See Also:

• The D2L chapter on Adagrad

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static final class	Adagrad.Builder	The Builder to construct an Adagrad object.

Nested classes/interfaces inherited from class ai.djl.training.optimizer.Optimizer

Optimizer.OptimizerBuilder<T extends Optimizer.OptimizerBuilder>

Field Summary

Fields inherited from class ai.djl.training.optimizer.Optimizer

clipGrad, rescaleGrad

Constructor Summary

Constructors

Modifier	Constructor	Description
protected	Adagrad(Adagrad.Builder builder)	Creates a new instance of Adam optimizer.

Method Summary

Modifier and Type	Method	Description
static Adagrad.Builder	builder()	Creates a builder to build a Adam.
void	update(String parameterId, NDArray weight, NDArray grad)	Updates the parameters according to the gradients.

Methods inherited from class ai.djl.training.optimizer.Optimizer

adadelta, adagrad, adam, adamW, getWeightDecay, nag, rmsprop, sgd, updateCount, withDefaultState

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Details

Adagrad

protected Adagrad(Adagrad.Builder builder)

Creates a new instance of Adam optimizer.

Parameters:

builder - the builder to create a new instance of Adam optimizer

Method Details

update

public void update(String parameterId,
 NDArray weight,
 NDArray grad)

Updates the parameters according to the gradients.

Specified by:

update in class Optimizer

Parameters:

parameterId - the parameter to be updated

weight - the weights of the parameter

grad - the gradients

builder

public static Adagrad.Builder builder()

Creates a builder to build a Adam.

Returns:

a new builder