Inheritance diagram for EffGlobalMinimizer:

Public Member Functions
	EffGlobalMinimizer (ProblemDescDB &problem_db, Model &model)
	standard constructor

	~EffGlobalMinimizer ()
	alternate constructor for instantiations "on the fly"

void	pre_run ()
	destructor

void	core_run ()
	core portion of run; implemented by all derived classes and may include pre/post steps in lieu of separate pre/post More...

void	post_run (std::ostream &s)
	post-run portion of run (optional); verbose to print results; re-implemented by Iterators that can read all Variables/Responses and perform final analysis phase in a standalone way More...

const Model &	algorithm_space_model () const

Private Member Functions
void	check_parallelism ()
	function that checks if model supports asynchronous parallelism

void	build_gp ()
	build initial GP approximations after initial sampling

void	batch_synchronous_ego ()
	synchronous batch-sequential implementation: main function

void	batch_asynchronous_ego ()
	synchronous batch-sequential implementation: main function

void	construct_batch_acquisition (size_t new_acq, size_t new_batch)
	construct a batch of points from performing acquisition cycles

void	construct_batch_exploration (size_t new_expl, size_t new_batch)
	construct a batch of points from performing exploration cycles

void	evaluate_batch (bool rebuild)
	evaluate batch in parallel and replace liar responses

bool	query_batch (bool rebuild)
	perform nonblocking synchronization for parallel evaluation of truth responses and replace liar responses for any completions More...

void	backfill_batch (size_t new_acq, size_t new_expl)
	backfill any completed truth response evaluations in case of nonblocking synchronization

void	launch_batch ()
	launch all jobs in the variables map queues

void	launch_single (const Variables &vars_star)
	launch a single job

void	process_truth_response_map (const IntResponseMap &truth_resp_map, bool rebuild)
	update approximation data and constraint penalties/multipliers based on new truth data

void	update_variable_maps (const IntResponseMap &truth_resp_map)
	update variable map queues based on completed jobs

bool	converged ()
	check convergence indicators to assess if EGO has converged

void	retrieve_final_results ()
	post-processing: retrieve and export best samples and responses

void	initialize_counters_limits ()
	initialize counters and limits used for assessing convergence

void	update_convergence_counters (const Variables &vars_star, const Response &resp_star)
	update counters used for assessing convergence

void	update_convergence_counters (const Variables &vars_star)
	update counters used for assessing convergence in variables

void	update_convergence_counters (const Response &resp_star)
	update counters used for assessing convergence in response

void	pop_liar_responses ()
	delete all liar responses

void	append_liar (const Variables &vars_star, int liar_id, bool rebuild)
	evaluate and append a liar response

int	extract_id (IntVarsMCIter it, const IntVariablesMap &map)
	manage special value when iterator has advanced to end

void	compute_best_sample ()
	determine meritFnStar from among the GP build data for use in EIF More...

void	extract_best_sample ()
	extract best solution from among the GP build data for final results More...

void	extract_qoi_build_data (size_t data_index, RealVector &fn_vals)
	extra response function build data from across the set of QoI

Real	augmented_lagrangian (const RealVector &mean)
	helper for evaluating the value of the augmented Lagrangian merit fn

void	update_constraints (const RealVector &fn_vals)
	update constraint penalties and multipliers for a single response

void	update_constraints (const IntResponseMap &truth_resp_map)
	update constraint penalties and multipliers for a set of responses

bool	empty_queues () const
	helper for checking queued jobs in vars{Acquisition,Exploration}Map

Real	compute_probability_improvement (const RealVector &means, const RealVector &variances)
	probability improvement (PI) function for the EGO PI acquisition function implementation More...

Real	compute_expected_improvement (const RealVector &means, const RealVector &variances)
	expected improvement (EI) function for the EGO EI acquisition function implementation More...

Real	compute_lower_confidence_bound (const RealVector &means, const RealVector &variances)
	lower confidence bound (LCB) function for the EGO LCB acquisition function implementation More...

Real	compute_variances (const RealVector &variances)
	variance function for the EGO MSE acquisition implementation More...

RealVector	expected_violation (const RealVector &means, const RealVector &variances)
	expected violation function for the constraint functions More...

void	update_penalty ()
	initialize and update the penaltyParameter

void	debug_print_values (const Variables &vars)
	print mean and variance if debug flag is ON

void	debug_print_dist_counters (Real dist_cv_star)
	print counters if debug flag is ON

void	debug_print_eif_counters (Real eif_star)
	print counters if debug flag is ON

void	debug_plots ()
	DEBUG_PLOTS conditional - output set of samples used to build the GP if problem is 2D.

Static Private Member Functions
static void	PIF_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 EGO More...

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 EGO More...

static void	LCB_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 Lower-Confidence Bound (LCB) problem formulation for EGO More...

static void	Variances_objective_eval (const Variables &sub_model_vars, const Variables &recast_vars, const Response &sub_model_response, Response &recast_response)
	Variance formulation for primary. More...

Private Attributes
Model	fHatModel
	GP model of response, one approximation per response function.

Model	approxSubProbModel
	recast model which assimilates either (a) mean and variance to solve the max(EIF) sub-problem (used by EIF_objective_eval()) or (b) variance alone for pure exploration (used by Variances_objective_eval())

Real	meritFnStar
	minimum penalized response from among truth build data

RealVector	prevSubProbSoln
	previous solution to EIF approximation sub-problem

short	dataOrder
	order of the data used for surrogate construction, in ActiveSet request vector 3-bit format; user may override responses spec

int	batchSize
	total batch size for parallel EGO

int	batchSizeAcquisition
	number of new sampling points defined from maximizing acquisition function

int	batchSizeExploration
	number of new sampling points defined from maximizing posterior variance

int	batchEvalId
	counter for incrementing evaluation ids to allow synchronization with iteratedModel ids across acquisition and exploration job queues

IntVariablesMap	varsAcquisitionMap
	variable sets for batch evaluation of truth model, accumulated by construct_batch_acquisition()

IntVariablesMap	varsExplorationMap
	variable sets for batch evaluation of truth model, accumulated by construct_batch_exploration()

bool	parallelFlag
	bool flag if model supports asynchronous parallelism

bool	batchAsynch
	algorithm option for fully asynchronous batch updating of the GP

Real	distanceTol
	convergence checkers tolerance convergence on distance between predicted best-so-far samples

unsigned short	eifConvergenceCntr
	counter for convergence in EIF

unsigned short	eifConvergenceLimit
	limit convergence (compared with counter) of EIF

unsigned short	distConvergenceCntr
	counter for distance in input space

unsigned short	distConvergenceLimit
	limit for distance (compared with counter) in input space

unsigned short	globalIterCount
	counter for global iteration

Static Private Attributes
static EffGlobalMinimizer *	effGlobalInstance
	pointer to the active object instance used within the static evaluator functions in order to avoid the need for static data

Additional Inherited Members
Static Public Member Functions inherited from Minimizer
static Real	sum_squared_residuals (size_t num_pri_fns, const RealVector &residuals, const RealVector &weights)
	return weighted sum of squared residuals

static void	print_residuals (size_t num_terms, const RealVector &best_terms, const RealVector &weights, size_t num_best, size_t best_index, std::ostream &s)
	print num_terms residuals and misfit for final results

static void	print_model_resp (size_t num_pri_fns, const RealVector &best_fns, size_t num_best, size_t best_index, std::ostream &s)
	print the original user model resp in the case of data transformations

Protected Member Functions inherited from SurrBasedMinimizer
	SurrBasedMinimizer (ProblemDescDB &problem_db, Model &model, std::shared_ptr< TraitsBase > traits)
	constructor

	~SurrBasedMinimizer ()
	destructor

void	derived_init_communicators (ParLevLIter pl_iter)
	derived class contributions to initializing the communicators associated with this Iterator instance

void	derived_set_communicators (ParLevLIter pl_iter)
	derived class contributions to setting the communicators associated with this Iterator instance

void	derived_free_communicators (ParLevLIter pl_iter)
	derived class contributions to freeing the communicators associated with this Iterator instance

void	print_results (std::ostream &s, short results_state=FINAL_RESULTS)

void	update_lagrange_multipliers (const RealVector &fn_vals, const RealMatrix &fn_grads, SurrBasedLevelData &tr_data)
	initialize and update Lagrange multipliers for basic Lagrangian More...

void	update_augmented_lagrange_multipliers (const RealVector &fn_vals)
	initialize and update the Lagrange multipliers for augmented Lagrangian More...

void	initialize_filter (SurrBasedLevelData &tr_data, const RealVector &fn_vals)
	(re-)initialize filter from a set of function values

bool	update_filter (SurrBasedLevelData &tr_data, const RealVector &fn_vals)
	update filter using a new set of function values More...

Real	lagrangian_merit (const RealVector &fn_vals, const BoolDeque &sense, const RealVector &primary_wts, const RealVector &nln_ineq_l_bnds, const RealVector &nln_ineq_u_bnds, const RealVector &nln_eq_tgts)
	compute a Lagrangian function from a set of function values More...

void	lagrangian_gradient (const RealVector &fn_vals, const RealMatrix &fn_grads, const BoolDeque &sense, const RealVector &primary_wts, const RealVector &nln_ineq_l_bnds, const RealVector &nln_ineq_u_bnds, const RealVector &nln_eq_tgts, RealVector &lag_grad)
	compute the gradient of the Lagrangian function

void	lagrangian_hessian (const RealVector &fn_vals, const RealMatrix &fn_grads, const RealSymMatrixArray &fn_hessians, const BoolDeque &sense, const RealVector &primary_wts, const RealVector &nln_ineq_l_bnds, const RealVector &nln_ineq_u_bnds, const RealVector &nln_eq_tgts, RealSymMatrix &lag_hess)
	compute the Hessian of the Lagrangian function

Real	augmented_lagrangian_merit (const RealVector &fn_vals, const BoolDeque &sense, const RealVector &primary_wts, const RealVector &nln_ineq_l_bnds, const RealVector &nln_ineq_u_bnds, const RealVector &nln_eq_tgts)
	compute an augmented Lagrangian function from a set of function values More...

void	augmented_lagrangian_gradient (const RealVector &fn_vals, const RealMatrix &fn_grads, const BoolDeque &sense, const RealVector &primary_wts, const RealVector &nln_ineq_l_bnds, const RealVector &nln_ineq_u_bnds, const RealVector &nln_eq_tgts, RealVector &alag_grad)
	compute the gradient of the augmented Lagrangian function

void	augmented_lagrangian_hessian (const RealVector &fn_vals, const RealMatrix &fn_grads, const RealSymMatrixArray &fn_hessians, const BoolDeque &sense, const RealVector &primary_wts, const RealVector &nln_ineq_l_bnds, const RealVector &nln_ineq_u_bnds, const RealVector &nln_eq_tgts, RealSymMatrix &alag_hess)
	compute the Hessian of the augmented Lagrangian function

Real	penalty_merit (const RealVector &fn_vals, const BoolDeque &sense, const RealVector &primary_wts)
	compute a penalty function from a set of function values More...

void	penalty_gradient (const RealVector &fn_vals, const RealMatrix &fn_grads, const BoolDeque &sense, const RealVector &primary_wts, RealVector &pen_grad)
	compute the gradient of the penalty function

Real	constraint_violation (const RealVector &fn_vals, const Real &constraint_tol)
	compute the constraint violation from a set of function values More...

Static Protected Member Functions inherited from Iterator
static void	gnewton_set_recast (const Variables &recast_vars, const ActiveSet &recast_set, ActiveSet &sub_model_set)
	conversion of request vector values for the Gauss-Newton Hessian approximation More...

Protected Attributes inherited from SurrBasedMinimizer
Iterator	approxSubProbMinimizer
	the minimizer used on the surrogate model to solve the approximate subproblem on each surrogate-based iteration

size_t	globalIterCount
	global iteration counter corresponding to number of surrogate-based minimizations

RealVector	lagrangeMult
	Lagrange multipliers for basic Lagrangian calculations.

RealVector	augLagrangeMult
	Lagrange multipliers for augmented Lagrangian calculations.

Real	penaltyParameter
	the penalization factor for violated constraints used in quadratic penalty calculations; increased in update_penalty()

RealVector	origNonlinIneqLowerBnds
	original nonlinear inequality constraint lower bounds (no relaxation)

RealVector	origNonlinIneqUpperBnds
	original nonlinear inequality constraint upper bounds (no relaxation)

RealVector	origNonlinEqTargets
	original nonlinear equality constraint targets (no relaxation)

Real	eta
	constant used in etaSequence updates

Real	alphaEta
	power for etaSequence updates when updating penalty

Real	betaEta
	power for etaSequence updates when updating multipliers

Real	etaSequence
	decreasing sequence of allowable constraint violation used in augmented Lagrangian updates (refer to Conn, Gould, and Toint, section 14.4)

size_t	miPLIndex
	index for the active ParallelLevel within ParallelConfiguration::miPLIters

Static Protected Attributes inherited from Minimizer
static Minimizer *	minimizerInstance
	pointer to Minimizer used in static member functions

Detailed Description

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.

Member Function Documentation

void core_run ( )

virtual

core portion of run; implemented by all derived classes and may include pre/post steps in lieu of separate pre/post

Virtual run function for the iterator class hierarchy. All derived classes need to redefine it.

Reimplemented from Iterator.

References EffGlobalMinimizer::batch_asynchronous_ego(), EffGlobalMinimizer::batch_synchronous_ego(), EffGlobalMinimizer::batchAsynch, EffGlobalMinimizer::build_gp(), and EffGlobalMinimizer::effGlobalInstance.

void post_run ( std::ostream & s)

virtual

post-run portion of run (optional); verbose to print results; re-implemented by Iterators that can read all Variables/Responses and perform final analysis phase in a standalone way

Post-run phase, which a derived iterator may optionally reimplement; when not present, post-run is likely integrated into run. This is a virtual function; when re-implementing, a derived class must call its nearest parent's post_run(), typically after performing its own implementation steps.

Reimplemented from Minimizer.

References EffGlobalMinimizer::approxSubProbModel, Model::finalize_mapping(), Minimizer::post_run(), and EffGlobalMinimizer::retrieve_final_results().

const Model & algorithm_space_model ( ) const

inlinevirtual

default definition that gets redefined in selected derived Minimizers

Reimplemented from Minimizer.

References EffGlobalMinimizer::fHatModel.

bool query_batch ( bool rebuild)

private

perform nonblocking synchronization for parallel evaluation of truth responses and replace liar responses for any completions

query running jobs and process any new completions

References Model::component_parallel_mode(), EffGlobalMinimizer::empty_queues(), EffGlobalMinimizer::fHatModel, Iterator::iteratedModel, EffGlobalMinimizer::process_truth_response_map(), Model::synchronize_nowait(), and EffGlobalMinimizer::update_variable_maps().

Referenced by EffGlobalMinimizer::batch_asynchronous_ego().

void compute_best_sample ( )

private

determine meritFnStar from among the GP build data for use in EIF

Extract the best merit function from build data through evaluaton of points on fHatModel. This merit fn value is used within the EIF during an approximate sub-problem solve.

References Model::approximation_data(), EffGlobalMinimizer::augmented_lagrangian(), Model::continuous_variables(), Model::current_response(), Model::evaluate(), EffGlobalMinimizer::fHatModel, Response::function_values(), EffGlobalMinimizer::meritFnStar, and Minimizer::numFunctions.

Referenced by EffGlobalMinimizer::construct_batch_acquisition().

void extract_best_sample ( )

private

extract best solution from among the GP build data for final results

Extract the best point from the build data for final results reporting.

References Model::approximation_data(), EffGlobalMinimizer::augmented_lagrangian(), Iterator::bestResponseArray, Iterator::bestVariablesArray, EffGlobalMinimizer::extract_qoi_build_data(), EffGlobalMinimizer::fHatModel, and Minimizer::numFunctions.

Referenced by EffGlobalMinimizer::retrieve_final_results().

Real compute_probability_improvement	(	const RealVector &	means,
		const RealVector &	variances
	)

private

probability improvement (PI) function for the EGO PI acquisition function implementation

Compute the PI acquisition function

References SurrBasedMinimizer::augLagrangeMult, EffGlobalMinimizer::expected_violation(), Iterator::iteratedModel, EffGlobalMinimizer::meritFnStar, Minimizer::numNonlinearConstraints, Minimizer::objective(), SurrBasedMinimizer::penaltyParameter, Model::primary_response_fn_sense(), and Model::primary_response_fn_weights().

Referenced by EffGlobalMinimizer::PIF_objective_eval().

Real compute_expected_improvement	(	const RealVector &	means,
		const RealVector &	variances
	)

private

expected improvement (EI) function for the EGO EI acquisition function implementation

Compute the EI acquisition function

References SurrBasedMinimizer::augLagrangeMult, EffGlobalMinimizer::expected_violation(), Iterator::iteratedModel, EffGlobalMinimizer::meritFnStar, Minimizer::numNonlinearConstraints, Minimizer::objective(), SurrBasedMinimizer::penaltyParameter, Model::primary_response_fn_sense(), and Model::primary_response_fn_weights().

Referenced by EffGlobalMinimizer::debug_plots(), and EffGlobalMinimizer::EIF_objective_eval().

Real compute_lower_confidence_bound	(	const RealVector &	means,
		const RealVector &	variances
	)

private

lower confidence bound (LCB) function for the EGO LCB acquisition function implementation

Compute the LCB acquisition function

References SurrBasedMinimizer::augLagrangeMult, EffGlobalMinimizer::expected_violation(), Iterator::iteratedModel, Minimizer::numNonlinearConstraints, Minimizer::objective(), SurrBasedMinimizer::penaltyParameter, Model::primary_response_fn_sense(), and Model::primary_response_fn_weights().

Referenced by EffGlobalMinimizer::LCB_objective_eval().

Real compute_variances ( const RealVector & variances)

private

variance function for the EGO MSE acquisition implementation

Compute the variances

Referenced by EffGlobalMinimizer::Variances_objective_eval().

RealVector expected_violation	(	const RealVector &	means,
		const RealVector &	variances
	)

private

expected violation function for the constraint functions

Compute the expected violation for constraints

References Minimizer::bigRealBoundSize, Minimizer::numNonlinearConstraints, Minimizer::numNonlinearEqConstraints, Minimizer::numNonlinearIneqConstraints, Minimizer::numUserPrimaryFns, SurrBasedMinimizer::origNonlinEqTargets, SurrBasedMinimizer::origNonlinIneqLowerBnds, and SurrBasedMinimizer::origNonlinIneqUpperBnds.

Referenced by EffGlobalMinimizer::compute_expected_improvement(), EffGlobalMinimizer::compute_lower_confidence_bound(), EffGlobalMinimizer::compute_probability_improvement(), and EffGlobalMinimizer::debug_print_values().

void PIF_objective_eval	(	const Variables &	sub_model_vars,
		const Variables &	recast_vars,
		const Response &	sub_model_response,
		Response &	recast_response
	)

staticprivate

static function used as the objective function in the Expected Improvement (EIF) problem formulation for EGO

To maximize expected improvement (PI), the approxSubProbMinimizer will minimize -(compute_probability_improvement).

References Response::active_set_request_vector(), Model::approximation_variances(), EffGlobalMinimizer::compute_probability_improvement(), EffGlobalMinimizer::effGlobalInstance, EffGlobalMinimizer::fHatModel, Response::function_value(), and Response::function_values().

void EIF_objective_eval	(	const Variables &	sub_model_vars,
		const Variables &	recast_vars,
		const Response &	sub_model_response,
		Response &	recast_response
	)

staticprivate

static function used as the objective function in the Expected Improvement (EIF) problem formulation for EGO

To maximize expected improvement (EI), the approxSubProbMinimizer will minimize -(compute_expected_improvement).

References Response::active_set_request_vector(), Model::approximation_variances(), EffGlobalMinimizer::compute_expected_improvement(), EffGlobalMinimizer::effGlobalInstance, EffGlobalMinimizer::fHatModel, Response::function_value(), and Response::function_values().

Referenced by EffGlobalMinimizer::construct_batch_acquisition().

void LCB_objective_eval	(	const Variables &	sub_model_vars,
		const Variables &	recast_vars,
		const Response &	sub_model_response,
		Response &	recast_response
	)

staticprivate

static function used as the objective function in the Lower-Confidence Bound (LCB) problem formulation for EGO

To maximize lower confidence bound (LCB), the approxSubProbMinimizer will minimize -(compute_lower_confidence_bound).

References Response::active_set_request_vector(), Model::approximation_variances(), EffGlobalMinimizer::compute_lower_confidence_bound(), EffGlobalMinimizer::effGlobalInstance, EffGlobalMinimizer::fHatModel, Response::function_value(), and Response::function_values().

void Variances_objective_eval	(	const Variables &	sub_model_vars,
		const Variables &	recast_vars,
		const Response &	sub_model_response,
		Response &	recast_response
	)

staticprivate

Variance formulation for primary.

To maximize variances, the approxSubProbMinimizer will minimize -(variances).

References Response::active_set_request_vector(), Model::approximation_variances(), EffGlobalMinimizer::compute_variances(), EffGlobalMinimizer::effGlobalInstance, EffGlobalMinimizer::fHatModel, and Response::function_value().

Referenced by EffGlobalMinimizer::construct_batch_exploration().

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

EffGlobalMinimizer.hpp
EffGlobalMinimizer.cpp

Public Member Functions

Private Member Functions

Static Private Member Functions

Private Attributes

Static Private Attributes

Additional Inherited Members

Detailed Description

Member Function Documentation