VPSApproximation Class Reference

Derived approximation class for VPS implementation. More...

Inheritance diagram for VPSApproximation:

List of all members.

Public Member Functions
	VPSApproximation ()
	default constructor
	VPSApproximation (const ProblemDescDB &problem_db, const SharedApproxData &shared_data)
	standard constructor (to call VPS from an input deck)
	VPSApproximation (const SharedApproxData &shared_data)
	Alternate constructor (to call VPS from another method like POF-darts)
	~VPSApproximation ()
	destructor
bool	VPS_execute ()
void	VPS_create_containers ()
void	VPS_retrieve_neighbors (size_t ipoint, bool update_point_neighbors)
void	VPS_adjust_extend_neighbors_of_all_points ()
void	VPS_extend_neighbors (size_t ipoint)
void	VPS_build_local_surrogate (size_t cell_index)
double	VPS_evaluate_surrogate (double *x)
void	VPS_destroy_global_containers ()
void	retrieve_permutations (size_t &m, size_t **&perm, size_t num_dim, size_t upper_bound, bool force_sum_constraint, size_t sum_constraint)
void	build_radial_basis_function (size_t icell)
void	VPS_LS_retrieve_weights (size_t cell_index)
double	evaluate_basis_function (double *x, size_t icell, size_t ibasis)
int	constrained_LeastSquare (size_t n, size_t m, double **H, double *w, double *f)
double	vec_dot_vec (size_t n, double *vec_a, double *vec_b)
double	vec_pow_vec (size_t num_dim, double *vec_a, size_t *vec_b)
bool	Cholesky (int n, double **A, double **LD)
void	Cholesky_solver (int n, double **LD, double *b, double *x)
void	GMRES (size_t n, double **A, double *b, double *x, double eps)
void	printMatrix (size_t m, size_t n, double **M)
void	initiate_random_number_generator (unsigned long x)
double	generate_a_random_number ()
size_t	retrieve_closest_cell (double *x)
bool	trim_line_using_Hyperplane (size_t num_dim, double *st, double *end, double *qH, double *nH)
double	f_test (double *x)
void	generate_poisson_disk_sample (double r)
void	generate_MC_sample ()
void	isocontouring (std::string file_name, bool plot_test_function, bool plot_surrogate, std::vector< double > contours)
void	isocontouring_solid (std::string file_name, bool plot_test_function, bool plot_surrogate, std::vector< double > contours)
void	plot_neighbors ()
Protected Member Functions
int	min_coefficients () const
	return the minimum number of samples (unknowns) required to build the derived class approximation type in numVars dimensions
int	num_constraints () const
	return the number of constraints to be enforced via an anchor point
void	build ()
	builds the approximation from scratch
Real	value (const Variables &vars)
	retrieve the predicted function value for a given parameter set
const RealVector &	gradient (const Variables &vars)
	retrieve the function gradient at the predicted value for a given parameter set
Real	prediction_variance (const Variables &vars)
	retrieve the variance of the predicted value for a given parameter set
Private Types
enum	subsurrogate { LS, GP }
enum	subsurrogate_basis { polynomial, radial }
enum	testfunction { SmoothHerbie, Herbie, UnitSphere }
Private Member Functions
void	VPSmodel_build ()
	Function to compute coefficients governing the VPS surrogates.
void	VPSmodel_apply (const RealVector &new_x, bool variance_flag, bool gradients_flag)
	Function returns a response value using the VPS surface.
Private Attributes
Real	approxValue
	value of the approximation returned by value()
Real	approxVariance
	value of the approximation returned by prediction_variance()
RealMatrix	trainPoints
	A 2-D array (num sample sites = rows, num vars = columns) used to create the Gaussian process.
RealMatrix	trainValues
	An array of response values; one response value per sample site.
size_t	numObs
	The number of observations on which the GP surface is built.
int	surrogateOrder
	The order of the polynomial in each Voronoi cell.
subsurrogate	_vps_subsurrogate
subsurrogate_basis	_vps_subsurrogate_basis
testfunction	_vps_test_function
double	Q [1220]
int	indx
double	cc
double	c
double	zc
double	zx
double	zy
size_t	qlen
size_t	_n_dim
double *	_xmin
double *	_xmax
double	_diag
size_t	_num_inserted_points
double **	_sample_points
double *	_fval
size_t **	_sample_neighbors
size_t **	_vps_ext_neighbors
size_t	_vps_order
size_t	_num_GMRES
size_t *	_num_cell_basis_functions
double *	_sample_vsize
double *	_vps_dfar
double ***	_sample_basis
double	_max_vsize
double	_disc_min_grad
double	_f_min
double	_f_max
size_t ***	_vps_t
double **	_vps_w
SharedApproxData	sharedData
std::vector< Approximation >	gpApproximations
Variables	gpEvalVars
Static Private Attributes
static VPSApproximation *	VPSinstance
	pointer to the active object instance used within the static evaluator

---

Detailed Description

Derived approximation class for VPS implementation.

The VPSApproximation class provides a set of piecewise surrogate approximations each of which is valid within a Voronoi cell.

---

Member Function Documentation

void VPSmodel_apply	(	const RealVector &	new_x,
		bool	variance_flag,
		bool	gradients_flag
	)		[private]

Function returns a response value using the VPS surface.

The response value is computed at the design point specified by the RealVector function argument.

References VPSApproximation::approxValue.

Referenced by VPSApproximation::gradient(), VPSApproximation::prediction_variance(), and VPSApproximation::value().

---

Member Data Documentation

VPSApproximation * VPSinstance [static, private]

pointer to the active object instance used within the static evaluator

default constructor

---

The documentation for this class was generated from the following files:

• VPSApproximation.hpp
• VPSApproximation.cpp