Class MultivariateFunctionMappingAdapter
 java.lang.Object

 org.apache.commons.math4.legacy.optim.nonlinear.scalar.MultivariateFunctionMappingAdapter

 All Implemented Interfaces:
MultivariateFunction
public class MultivariateFunctionMappingAdapter extends Object implements MultivariateFunction
Adapter for mapping bounded
MultivariateFunction
to unbounded ones.This adapter can be used to wrap functions subject to simple bounds on parameters so they can be used by optimizers that do not directly support simple bounds.
The principle is that the user function that will be wrapped will see its parameters bounded as required, i.e when its
value
method is called with argument arraypoint
, the elements array will fulfill requirementlower[i] <= point[i] <= upper[i]
for all i. Some of the components may be unbounded or bounded only on one side if the corresponding bound is set to an infinite value. The optimizer will not manage the user function by itself, but it will handle this adapter and it is this adapter that will take care the bounds are fulfilled. The adaptervalue(double[])
method will be called by the optimizer with unbound parameters, and the adapter will map the unbounded value to the bounded range using appropriate functions likeSigmoid
for double bounded elements for example.As the optimizer sees only unbounded parameters, it should be noted that the start point or simplex expected by the optimizer should be unbounded, so the user is responsible for converting his bounded point to unbounded by calling
boundedToUnbounded(double[])
before providing them to the optimizer. For the same reason, the point returned by the#optimize(org.apache.commons.math4.legacy.optim.OptimizationData...)
method is unbounded. So to convert this point to bounded, users must callunboundedToBounded(double[])
by themselves!This adapter is only a poor man solution to simple bounds optimization constraints that can be used with simple optimizers like
SimplexOptimizer
. A better solution is to use an optimizer that directly supports simple bounds likeCMAESOptimizer
orBOBYQAOptimizer
. One caveat of this poorman's solution is that behavior near the bounds may be numerically unstable as bounds are mapped from infinite values. Another caveat is that convergence values are evaluated by the optimizer with respect to unbounded variables, so there will be scales differences when converted to bounded variables. Since:
 3.0
 See Also:
MultivariateFunctionPenaltyAdapter


Constructor Summary
Constructors Constructor Description MultivariateFunctionMappingAdapter(MultivariateFunction bounded, double[] lower, double[] upper)
Simple constructor.

Method Summary
All Methods Instance Methods Concrete Methods Modifier and Type Method Description double[]
boundedToUnbounded(double[] point)
Maps an array from bounded to unbounded.double[]
unboundedToBounded(double[] point)
Maps an array from unbounded to bounded.double
value(double[] point)
Compute the underlying function value from an unbounded point.



Constructor Detail

MultivariateFunctionMappingAdapter
public MultivariateFunctionMappingAdapter(MultivariateFunction bounded, double[] lower, double[] upper)
Simple constructor. Parameters:
bounded
 bounded functionlower
 lower bounds for each element of the input parameters array (some elements may be set toDouble.NEGATIVE_INFINITY
for unbounded values)upper
 upper bounds for each element of the input parameters array (some elements may be set toDouble.POSITIVE_INFINITY
for unbounded values) Throws:
DimensionMismatchException
 if lower and upper bounds are not consistent, either according to dimension or to values


Method Detail

unboundedToBounded
public double[] unboundedToBounded(double[] point)
Maps an array from unbounded to bounded. Parameters:
point
 Unbounded values. Returns:
 the bounded values.

boundedToUnbounded
public double[] boundedToUnbounded(double[] point)
Maps an array from bounded to unbounded. Parameters:
point
 Bounded values. Returns:
 the unbounded values.

value
public double value(double[] point)
Compute the underlying function value from an unbounded point.This method simply bounds the unbounded point using the mappings set up at construction and calls the underlying function using the bounded point.
 Specified by:
value
in interfaceMultivariateFunction
 Parameters:
point
 unbounded value Returns:
 underlying function value
 See Also:
unboundedToBounded(double[])

