Dakota
Version 6.21
Explore and Predict with Confidence
|
Base class for discrepancy corrections. More...
Public Member Functions | |
DiscrepancyCorrection () | |
default constructor | |
DiscrepancyCorrection (Model &surr_model, const SizetSet &surr_fn_indices, short corr_type, short corr_order, String approx_type="local_taylor", short approx_order=SHRT_MAX) | |
standard constructor | |
DiscrepancyCorrection (const SizetSet &surr_fn_indices, size_t num_fns, size_t num_vars, short corr_type, short corr_order, String approx_type="local_taylor", short approx_order=SHRT_MAX) | |
alternate constructor | |
~DiscrepancyCorrection () | |
destructor | |
void | initialize (Model &surr_model, const SizetSet &surr_fn_indices, short corr_type, short corr_order, String approx_type="local_taylor", short approx_order=SHRT_MAX) |
initialize the DiscrepancyCorrection data | |
void | initialize (const SizetSet &surr_fn_indices, size_t num_fns, size_t num_vars, short corr_type, short corr_order, String approx_type="local_taylor", short approx_order=SHRT_MAX) |
initialize the DiscrepancyCorrection data | |
void | compute (const Variables &vars, const Response &truth_response, const Response &approx_response, bool quiet_flag=false) |
compute the correction required to bring approx_response into agreement with truth_response and store in {add,mult}Corrections More... | |
void | compute (const Response &truth_response, const Response &approx_response, Response &discrepancy_response, bool quiet_flag=false) |
compute the correction required to bring approx_response into agreement with truth_response and store in discrepancy_response | |
void | compute (const VariablesArray &vars_array, const ResponseArray &truth_response_array, const ResponseArray &approx_response, bool quiet_flag=false) |
compute the correction required to bring approx_response into agreement with truth_response as a function of the variables and store in {add,mult}Corrections | |
void | apply (const Variables &vars, Response &approx_response, bool quiet_flag=false) |
apply the correction computed in compute() to approx_response | |
void | compute_variance (const VariablesArray &vars_array, RealMatrix &approx_variance, bool quiet_flag=false) |
compute the variance of approx_response | |
void | correction_type (short corr_type) |
update correctionType | |
short | correction_type () const |
return correctionType | |
void | correction_order (short order) |
update correctionOrder | |
short | correction_order () const |
return correctionOrder | |
void | data_order (short order) |
update dataOrder | |
short | data_order () const |
return dataOrder | |
bool | computed () const |
return correctionComputed | |
bool | initialized () const |
return initializedFlag | |
Protected Attributes | |
SizetSet | surrogateFnIndices |
for mixed response sets, this array specifies the response function subset that is approximated | |
bool | initializedFlag |
indicates that discrepancy correction instance has been initialized following construction | |
short | correctionType |
approximation correction approach to be used: NO_CORRECTION, ADDITIVE_CORRECTION, MULTIPLICATIVE_CORRECTION, or COMBINED_CORRECTION. | |
short | correctionOrder |
approximation correction order to be used: 0, 1, or 2 | |
short | dataOrder |
order of correction data in 3-bit format: overlay of 1 (value), 2 (gradient), and 4 (Hessian) | |
bool | correctionComputed |
flag indicating whether or not a correction has been computed and is available for application | |
size_t | numFns |
total number of response functions (of which surrogateFnIndices may define a subset) | |
size_t | numVars |
number of continuous variables active in the correction | |
Private Member Functions | |
void | initialize (short corr_type, short corr_order, String approx_type, short approx_order) |
initialize types and orders | |
void | initialize_corrections () |
internal convenience function shared by overloaded initialize() variants | |
bool | check_multiplicative (const RealVector &truth_fns, const RealVector &approx_fns) |
define badScalingFlag | |
void | compute_additive (const Response &truth_response, const Response &approx_response, int index, Real &discrep_fn, RealVector &discrep_grad, RealSymMatrix &discrep_hess) |
internal convenience function for computing additive corrections between truth and approximate responses | |
void | compute_multiplicative (const Response &truth_response, const Response &approx_response, int index, Real &discrep_fn, RealVector &discrep_grad, RealSymMatrix &discrep_hess) |
internal convenience function for computing multiplicative corrections between truth and approximate responses | |
void | apply_additive (const Variables &vars, Response &approx_response) |
internal convenience function for applying additive corrections to an approximate response | |
void | apply_multiplicative (const Variables &vars, Response &approx_response) |
internal convenience function for applying multiplicative corrections to an approximate response | |
void | apply_additive (const Variables &vars, RealVector &approx_fns) |
internal convenience function for applying additive corrections to a set of response functions | |
void | apply_multiplicative (const Variables &vars, RealVector &approx_fns) |
internal convenience function for applying multiplicative corrections to a set of response functions | |
const Response & | search_db (const Variables &search_vars, const ShortArray &search_asv) |
search data_pairs for missing approximation data | |
Private Attributes | |
Pecos::DiscrepancyCalculator | discrepCalc |
helper utility for calculating discrepancies | |
bool | badScalingFlag |
flag used to indicate function values near zero for multiplicative corrections; triggers an automatic switch to additive corrections | |
bool | computeAdditive |
flag indicating the need for additive correction calculations | |
bool | computeMultiplicative |
flag indicating the need for multiplicative correction calculations | |
String | approxType |
string indicating the discrepancy approximation type | |
short | approxOrder |
polynomial order of the discrepancy approximation (basis or trend order) | |
bool | addAnchor |
flag indicating that data additions are anchor points (for updating local and multipoint approximations) | |
SharedApproxData | sharedData |
data that is shared among all correction Approximations | |
std::vector< Approximation > | addCorrections |
array of additive corrections; surrogate models of a model discrepancy function (formed from model differences) | |
std::vector< Approximation > | multCorrections |
array of multiplicative corrections; surrogate models of a model discrepancy function (formed from model ratios) | |
Model | surrModel |
shallow copy of the surrogate model instance as returned by Model::surrogate_model() (the DataFitSurrModel or or one of EnsembleSurrModel::approxModels) | |
RealVector | combineFactors |
factors for combining additive and multiplicative corrections. Each factor is the weighting applied to the additive correction and 1.-factor is the weighting applied to the multiplicative correction. The factor value is determined by an additional requirement to match the high fidelity function value at the previous correction point (e.g., previous trust region center). This results in a multipoint correction instead of a strictly local correction. | |
Variables | correctionPrevCenterPt |
copy of center point from the previous correction cycle | |
RealVector | truthFnsCenter |
truth function values at the current correction point | |
RealVector | approxFnsCenter |
Surrogate function values at the current correction point. | |
RealMatrix | approxGradsCenter |
Surrogate gradient values at the current correction point. | |
RealVector | truthFnsPrevCenter |
copy of truth function values at center of previous correction cycle | |
RealVector | approxFnsPrevCenter |
copy of approximate function values at center of previous correction cycle | |
Base class for discrepancy corrections.
The DiscrepancyCorrection class provides common functions for computing and applying corrections to approximations.
void compute | ( | const Variables & | vars, |
const Response & | truth_response, | ||
const Response & | approx_response, | ||
bool | quiet_flag = false |
||
) |
compute the correction required to bring approx_response into agreement with truth_response and store in {add,mult}Corrections
Compute an additive or multiplicative correction that corrects the approx_response to have 0th-order consistency (matches values), 1st-order consistency (matches values and gradients), or 2nd-order consistency (matches values, gradients, and Hessians) with the truth_response at a single point (e.g., the center of a trust region). The 0th-order, 1st-order, and 2nd-order corrections use scalar values, linear scaling functions, and quadratic scaling functions, respectively, for each response function.
References Response::active_set(), Approximation::add(), DiscrepancyCorrection::addAnchor, DiscrepancyCorrection::addCorrections, DiscrepancyCorrection::apply(), DiscrepancyCorrection::apply_additive(), DiscrepancyCorrection::apply_multiplicative(), DiscrepancyCorrection::approxFnsCenter, DiscrepancyCorrection::approxFnsPrevCenter, DiscrepancyCorrection::approxGradsCenter, DiscrepancyCorrection::badScalingFlag, Approximation::clear_current_active_data(), DiscrepancyCorrection::combineFactors, DiscrepancyCorrection::computeAdditive, DiscrepancyCorrection::computeMultiplicative, Variables::continuous_variables(), Response::copy(), DiscrepancyCorrection::correctionComputed, DiscrepancyCorrection::correctionOrder, DiscrepancyCorrection::correctionPrevCenterPt, DiscrepancyCorrection::correctionType, DiscrepancyCorrection::dataOrder, DiscrepancyCorrection::discrepCalc, Variables::discrete_int_variables(), Variables::discrete_real_variables(), Response::function_gradient_view(), Response::function_gradients(), Response::function_hessian(), Response::function_value(), Response::function_values(), Model::is_null(), DiscrepancyCorrection::multCorrections, DiscrepancyCorrection::numFns, DiscrepancyCorrection::numVars, ActiveSet::request_values(), DiscrepancyCorrection::sharedData, DiscrepancyCorrection::surrModel, DiscrepancyCorrection::surrogateFnIndices, DiscrepancyCorrection::truthFnsCenter, and DiscrepancyCorrection::truthFnsPrevCenter.
Referenced by DiscrepancyCorrection::compute(), EnsembleSurrModel::compute_apply_delta(), DataFitSurrModel::derived_evaluate(), DataFitSurrModel::derived_synchronize(), DataFitSurrModel::derived_synchronize_nowait(), and EnsembleSurrModel::single_apply().