Public Member Functions | Private Member Functions | Static Private Member Functions | Private Attributes | Static Private Attributes
EffGlobalMinimizer Class Reference

Implementation of Efficient Global Optimization/Least Squares algorithms. More...

Inheritance diagram for EffGlobalMinimizer:
SurrBasedMinimizer Minimizer Iterator

List of all members.

Public Member Functions

 EffGlobalMinimizer (Model &model)
 standard constructor
 ~EffGlobalMinimizer ()
 alternate constructor for instantiations "on the fly"
void minimize_surrogates ()
 Used for computing the optimal solution using a surrogate-based approach. Redefines the Iterator::run() virtual function.
const Modelalgorithm_space_model () const
 return the result of any recasting or surrogate model recursion layered on top of iteratedModel by the derived Iterator ctor chain

Private Member Functions

void minimize_surrogates_on_model ()
 called by minimize_surrogates for setUpType == "model"
void get_best_sample ()
 called by minimize_surrogates for setUpType == "user_functions"
Real expected_improvement (const RealVector &means, const RealVector &variances)
 expected improvement function for the GP
RealVector expected_violation (const RealVector &means, const RealVector &variances)
 expected violation function for the constraint functions
void update_penalty ()
 initialize and update the penaltyParameter

Static Private Member Functions

static void EIF_objective_eval (const Variables &sub_model_vars, const Variables &recast_vars, const Response &sub_model_response, Response &recast_response)
 static function used as the objective function in the Expected Improvement (EIF) problem formulation for PMA

Private Attributes

String setUpType
 controls iteration mode: "model" (normal usage) or "user_functions" (user-supplied functions mode for "on the fly" instantiations).
Model fHatModel
 GP model of response, one approximation per response function.
Model eifModel
 recast model which assimilates mean and variance to solve the max(EIF) sub-problem
Real meritFnStar
 minimum penalized response from among true function evaluations
RealVector truthFnStar
 true function values corresponding to the minimum penalized response
RealVector varStar
 point that corresponds to the optimal value meritFnStar
short dataOrder
 order of the data used for surrogate construction, in ActiveSet request vector 3-bit format; user may override responses spec

Static Private Attributes

static EffGlobalMinimizereffGlobalInstance
 pointer to the active object instance used within the static evaluator functions in order to avoid the need for static data

Detailed Description

Implementation of Efficient Global Optimization/Least Squares algorithms.

The EffGlobalMinimizer class provides an implementation of the Efficient Global Optimization algorithm developed by Jones, Schonlau, & Welch as well as adaptation of the concept to nonlinear least squares.


Constructor & Destructor Documentation

alternate constructor for instantiations "on the fly"

destructor

This is an alternate constructor for instantiations on the fly using a Model but no ProblemDescDB.

References SurrBasedMinimizer::approxSubProbMinimizer, EffGlobalMinimizer::eifModel, Model::free_communicators(), and Iterator::maximum_concurrency().


Member Function Documentation

void get_best_sample ( ) [private]

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