SG++-Doxygen-Documentation
|
Sparse grid interpolant of a vector-valued function. More...
#include <InterpolantVectorFunction.hpp>
Public Member Functions | |
void | clone (std::unique_ptr< VectorFunction > &clone) const override |
void | eval (const base::DataVector &x, base::DataVector &value) override |
Evaluation of the function. More... | |
const base::DataMatrix & | getAlpha () const |
InterpolantVectorFunction (base::Grid &grid, const base::DataMatrix &alpha) | |
Constructor. More... | |
void | setAlpha (const base::DataMatrix &alpha) |
~InterpolantVectorFunction () override | |
Destructor. More... | |
Public Member Functions inherited from sgpp::optimization::VectorFunction | |
size_t | getNumberOfComponents () const |
size_t | getNumberOfParameters () const |
VectorFunction (size_t d, size_t m) | |
Constructor. More... | |
virtual | ~VectorFunction () |
Destructor. More... | |
Protected Attributes | |
base::DataMatrix | alpha |
coefficient matrix More... | |
base::Grid & | grid |
sparse grid More... | |
std::unique_ptr< base::OperationEval > | opEval |
pointer to evaluation operation More... | |
Protected Attributes inherited from sgpp::optimization::VectorFunction | |
size_t | d |
dimension of the domain More... | |
size_t | m |
number of components More... | |
Sparse grid interpolant of a vector-valued function.
More generally, the function can be any linear combination \(g\colon [0, 1]^d \to \mathbb{R}^m\), \(g_j(\vec{x}) = \sum_{k=1}^N \alpha_{k,j} \varphi_k(\vec{x})\) of the basis functions \(\varphi_k = \varphi_{\vec{\ell}_k,\vec{i}_k}\) of a sparse grid with grid points \(\vec{x}_k = \vec{x}_{\vec{\ell}_k,\vec{i}_k}\). But most often, the function (e.g., its coefficients) is constructed as an interpolant at the grid points for some function values.
|
inline |
Constructor.
Do not destruct the grid before the InterpolantVectorFunction object!
grid | sparse grid |
alpha | coefficient matrix (j-th column contains hierarchical surplusses \(\alpha_{\cdot,j}\) of \(g_j\)) |
Referenced by clone().
|
inlineoverride |
Destructor.
|
inlineoverridevirtual |
[out] | clone | pointer to cloned object |
Implements sgpp::optimization::VectorFunction.
References alpha, grid, and InterpolantVectorFunction().
|
inlineoverridevirtual |
Evaluation of the function.
[in] | x | evaluation point \(\vec{x} \in [0, 1]^d\) |
[out] | value | \(g(\vec{x})\) |
Implements sgpp::optimization::VectorFunction.
References alpha, sgpp::optimization::VectorFunction::d, opEval, and sgpp::base::DataVector::setAll().
|
inline |
References alpha.
|
inline |
alpha | coefficient matrix |
References alpha.
|
protected |
coefficient matrix
Referenced by clone(), eval(), getAlpha(), python.learner.Classifier.Classifier::refineGrid(), and setAlpha().
|
protected |
sparse grid
Referenced by clone(), python.uq.learner.Interpolant.Interpolant::doLearningIteration(), python.learner.Classifier.Classifier::evalError(), python.uq.learner.Interpolant.Interpolant::evalError(), python.uq.learner.SimulationLearner.SimulationLearner::getCollocationNodes(), python.uq.learner.SimulationLearner.SimulationLearner::getGrid(), python.uq.learner.SimulationLearner.SimulationLearner::getLearner(), python.uq.learner.Regressor.Regressor::learnData(), python.uq.learner.Regressor.Regressor::learnDataWithFolding(), python.uq.learner.Regressor.Regressor::learnDataWithTest(), python.learner.Classifier.Classifier::refineGrid(), python.learner.Regressor.Regressor::refineGrid(), python.uq.learner.Regressor.Regressor::refineGrid(), python.uq.learner.SimulationLearner.SimulationLearner::refineGrid(), python.learner.Classifier.Classifier::updateResults(), python.learner.Regressor.Regressor::updateResults(), and python.uq.learner.Regressor.Regressor::updateResults().
|
protected |
pointer to evaluation operation
Referenced by eval().