jsat.regression

Class StochasticRidgeRegression

java.lang.Object

jsat.regression.StochasticRidgeRegression

All Implemented Interfaces:

java.io.Serializable, java.lang.Cloneable, Parameterized, Regressor, SimpleWeightVectorModel, SingleWeightVectorModel

public class StochasticRidgeRegression
extends java.lang.Object
implements Regressor, Parameterized, SingleWeightVectorModel

A Stochastic implementation of Ridge Regression. Ridge Regression is equivalent to MultipleLinearRegression with an added L₂ penalty for the weight vector.

This algorithm works best for problems with a large number of data points or very high dimensional problems.

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor and Description
StochasticRidgeRegression(double lambda, int epochs, int batchSize, double learningRate) Creates a new stochastic Ridge Regression learner that does not use a decay rate
StochasticRidgeRegression(double lambda, int epochs, int batchSize, double learningRate, DecayRate learningDecay) Creates a new stochastic Ridge Regression learner

Method Summary

Modifier and Type	Method and Description
StochasticRidgeRegression	clone()
int	getBatchSize() Returns the batch size for updates
double	getBias() Returns the bias term used for the model, or 0 of the model does not support or was not trained with a bias term.
double	getBias(int index) Returns the bias term used with the weight vector for the given class index.
int	getEpochs() Returns the number of training iterations
double	getLambda() Returns the regularization constant in use
DecayRate	getLearningDecay() Returns the learning decay rate used
double	getLearningRate() Returns the learning rate in use.
Vec	getRawWeight() Returns the only weight vector used for the model
Vec	getRawWeight(int index) Returns the raw weight vector associated with the given class index.
int	numWeightsVecs() Returns the number of weight vectors that can be returned.
double	regress(DataPoint data)
void	setBatchSize(int batchSize) Sets the batch size to learn from.
void	setEpochs(int epochs) Sets the number of iterations through the whole training set that will be performed.
void	setLambda(double lambda) Sets the regularization parameter used.
void	setLearningDecay(DecayRate learningDecay) Sets the learning rate decay function to use.
void	setLearningRate(double learningRate) Sets the learning rate used, and should be in the range (0, 1).
boolean	supportsWeightedData()
void	train(RegressionDataSet dataSet)
void	train(RegressionDataSet dataSet, boolean parallel)

Methods inherited from class java.lang.Object

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

Methods inherited from interface jsat.parameters.Parameterized

getParameter, getParameters

Constructor Detail

StochasticRidgeRegression

public StochasticRidgeRegression(double lambda,
                                 int epochs,
                                 int batchSize,
                                 double learningRate)

Creates a new stochastic Ridge Regression learner that does not use a decay rate

Parameters:

lambda - the regularization term

epochs - the number of training epochs to perform

batchSize - the batch size for updates

learningRate - the learning rate

StochasticRidgeRegression

public StochasticRidgeRegression(double lambda,
                                 int epochs,
                                 int batchSize,
                                 double learningRate,
                                 DecayRate learningDecay)

Creates a new stochastic Ridge Regression learner

Parameters:

lambda - the regularization term

epochs - the number of training epochs to perform

batchSize - the batch size for updates

learningRate - the learning rate

learningDecay - the learning rate decay

Method Detail

setLambda

public void setLambda(double lambda)

Sets the regularization parameter used.

Parameters:

lambda - the positive regularization constant in (0, Inf)

getLambda

public double getLambda()

Returns the regularization constant in use

Returns:

the regularization constant in use

setLearningRate

public void setLearningRate(double learningRate)

Sets the learning rate used, and should be in the range (0, 1).

Parameters:

learningRate - the learning rate to use

getLearningRate

public double getLearningRate()

Returns the learning rate in use.

Returns:

the learning rate to use.

setLearningDecay

public void setLearningDecay(DecayRate learningDecay)

Sets the learning rate decay function to use. The decay is applied after each epoch through the data set. Using a decay rate can reduce the time to converge and quality of the solution for difficult problems.

Parameters:

learningDecay - the decay function to apply to the learning rate

getLearningDecay

public DecayRate getLearningDecay()

Returns the learning decay rate used

Returns:

the learning decay rate used

setBatchSize

public void setBatchSize(int batchSize)

Sets the batch size to learn from. If larger than the training set, the problem will reduce to classic gradient descent.

Parameters:

batchSize - the number of training points to use in each batch update

getBatchSize

public int getBatchSize()

Returns the batch size for updates

Returns:

the batch size for updates

setEpochs

public void setEpochs(int epochs)

Sets the number of iterations through the whole training set that will be performed.

Parameters:

epochs - the number of training iterations

getEpochs

public int getEpochs()

Returns the number of training iterations

Returns:

the number of training iterations

getRawWeight

public Vec getRawWeight()

Description copied from interface: SingleWeightVectorModel

Returns the only weight vector used for the model

Specified by:

getRawWeight in interface SingleWeightVectorModel

Returns:

the only weight vector used for the model

getBias

public double getBias()

Description copied from interface: SingleWeightVectorModel

Returns the bias term used for the model, or 0 of the model does not support or was not trained with a bias term.

Specified by:

getBias in interface SingleWeightVectorModel

Returns:

the bias term for the model

getRawWeight

public Vec getRawWeight(int index)

Description copied from interface: SimpleWeightVectorModel

Returns the raw weight vector associated with the given class index. If the given class is an implicit zero vector, a ConstantVector object may be returned.
Do not alter the returned weight vector, as it will change the model's values.

If a regression problem, only index = 0 should be used

Specified by:

getRawWeight in interface SimpleWeightVectorModel

Parameters:

index - the class index to get the weight vector for

Returns:

the weight vector used for the specified class

getBias

public double getBias(int index)

Description copied from interface: SimpleWeightVectorModel

Returns the bias term used with the weight vector for the given class index. If the model does not support or was not trained with bias weights, 0 will be returned.

If a regression problem, only index = 0 should be used

Specified by:

getBias in interface SimpleWeightVectorModel

Parameters:

index - the class index to get the weight vector for

Returns:

the bias term for the specified class

numWeightsVecs

public int numWeightsVecs()

Description copied from interface: SimpleWeightVectorModel

Returns the number of weight vectors that can be returned. For binary classification problems the value may be 1 if only a single weight vector's sign is used to determine the class. For multi-class problems, the weight vector count includes the implicit zero vector (if one is being used).

Specified by:

numWeightsVecs in interface SimpleWeightVectorModel

Returns:

the number of weight vectors for which SimpleWeightVectorModel.getRawWeight(int) can be called.

regress

public double regress(DataPoint data)

Specified by:

regress in interface Regressor

train

public void train(RegressionDataSet dataSet,
                  boolean parallel)

Specified by:

train in interface Regressor

train

public void train(RegressionDataSet dataSet)

Specified by:

train in interface Regressor

supportsWeightedData

public boolean supportsWeightedData()

Specified by:

supportsWeightedData in interface Regressor

clone

public StochasticRidgeRegression clone()

Specified by:

clone in interface Regressor

Overrides:

clone in class java.lang.Object