Package ai.djl.training.optimizer

Class Nag

java.lang.Object

ai.djl.training.optimizer.Optimizer

ai.djl.training.optimizer.Nag

public class Nag
extends Optimizer

Nag is a Nesterov accelerated gradient optimizer.

This optimizer updates each weight by:
\( state = momentum * state + grad + wd *weight\)
\( weight = weight - (lr * (grad + momentum * state))

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	Nag.Builder	The Builder to construct an Nag 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	Nag(Nag.Builder builder)	Creates a new instance of Nag optimizer.

Method Summary

Modifier and Type	Method	Description
void	update(java.lang.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 Detail

Nag

protected Nag(Nag.Builder builder)

Creates a new instance of Nag optimizer.

Parameters:

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

Method Detail

update

public void update(java.lang.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