Package pulse.search.statistics

Class RegularisedLeastSquares

java.lang.Object

pulse.util.UpwardsNavigable

pulse.util.Group

pulse.util.Accessible

pulse.util.PropertyHolder

pulse.search.statistics.Statistic

pulse.search.statistics.ResidualStatistic

pulse.search.statistics.OptimiserStatistic

pulse.search.statistics.SumOfSquares

pulse.search.statistics.RegularisedLeastSquares

All Implemented Interfaces:

Serializable, Descriptive, Reflexive

public class RegularisedLeastSquares
extends SumOfSquares

This is an experimental feature. The objective function here is equal to the ordinary least-square (OLS) plus a penalising term proportional to the squared length of a search vector. This way, search vectors of lower dimensionality are favoured.

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor	Description
RegularisedLeastSquares()
RegularisedLeastSquares(RegularisedLeastSquares rls)

Method Summary

Modifier and Type	Method	Description
OptimiserStatistic	copy()
void	evaluate(GeneralTask t)	Calculates the sum of squared deviations using curve as reference.
String	getDescriptor()	If not null, will return the prefix, otherwise calls the superclass method.
double	getLambda()	The lambda is the regularisation strength.
void	setLambda(double lambda)

Methods inherited from class pulse.search.statistics.SumOfSquares

variance

Methods inherited from class pulse.search.statistics.OptimiserStatistic

getSelectedOptimiserDescriptor, setSelectedOptimiserDescriptor

Methods inherited from class pulse.search.statistics.ResidualStatistic

calculateResiduals, calculateResiduals, calculateResiduals, equals, getResiduals, getStatistic, getTimeSequence, hashCode, residualsArray, set, setStatistic

Methods inherited from class pulse.util.PropertyHolder

addListener, areDetailsHidden, data, describe, firePropertyChanged, getListeners, getPrefix, ignoreSiblings, initListeners, isListedNumericType, isListedParameter, listedKeywords, listedTypes, numericData, parameterListChanged, removeListeners, setPrefix, updateProperties, updateProperty

Methods inherited from class pulse.util.Accessible

accessibleChildren, genericProperties, genericProperty, numericProperties, numericProperty, property, update, update

Methods inherited from class pulse.util.Group

access, children, contents, getSimpleName, subgroups

Methods inherited from class pulse.util.UpwardsNavigable

addHierarchyListener, getHierarchyListeners, getParent, identify, removeHierarchyListener, removeHierarchyListeners, setParent, specificAncestor, tellParent

Methods inherited from class java.lang.Object

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

Constructor Detail

RegularisedLeastSquares

public RegularisedLeastSquares()

RegularisedLeastSquares

public RegularisedLeastSquares(RegularisedLeastSquares rls)

Method Detail

getLambda

public double getLambda()

The lambda is the regularisation strength.

Returns:

the lambda factor.

setLambda

public void setLambda(double lambda)

evaluate

public void evaluate(GeneralTask t)

Description copied from class: SumOfSquares

Calculates the sum of squared deviations using curve as reference.

This calculates $\sum _{i=i_1}^{i_2}\left(\overbrace{T}\right(t_i)-T(t_i{)}^{ref}{)}^2$, where $T_i^{ref}$ is the temperature value corresponding to the time at index i for the reference curve. Note that the time $t_i$ corresponds to the reference's time list, which generally does not match to that of this heating curve. The $\overbrace{T}\left(t_i\right)$ is the interpolated value.

Overrides:

evaluate in class SumOfSquares

Parameters:

t - The task containing the reference and calculated curves

See Also:

calculateResiduals()

getDescriptor

public String getDescriptor()

Description copied from class: PropertyHolder

If not null, will return the prefix, otherwise calls the superclass method.

Overrides:

getDescriptor in class SumOfSquares

Returns:

the descriptor

See Also:

Group.getSimpleName()

copy

public OptimiserStatistic copy()

Overrides:

copy in class SumOfSquares