use_surrogate

Surrogate model usage mode for mesh adaptive search

Specification

• Alias: None

• Arguments: None

• Default: optimize

Child Keywords:

Required/Optional	Description of Group	Dakota Keyword	Dakota Keyword Description
Required (Choose One)	Surrogate Purpose	inform_search	Surrogate informs evaluation order in mesh adaptive search
		optimize	Surrogate is used in lieu of true model for mesh adaptive search

Description

The use_surrogate keyword is used to define how a surrogate model (if one is provided) is to be used by mesh_adaptive_search. There are two approaches available: inform_search uses the surrogate to sort list of trial points and subsequently the true function is evaluated on the most promising points first. Both true function and surrogate are used interchangeably within the method. optimize forces the use of a surrogate in lieu of the true model and thus the true function is never invoked except to construct the surrogate.

Known Issue: When using discrete variables, there have been sometimes significant differences in surrogate behavior observed across computing platforms in some cases. The cause has not yet been fully diagnosed and is currently under investigation. In addition, guidance on appropriate construction and use of surrogates with discrete variables is under development. In the meantime, users should therefore be aware that there is a risk of inaccurate results when using surrogates with discrete variables.

Default Behavior

By default, mesh_adaptive_search follows behaviour provided by optimize option.

Examples

The following example shows the syntax used to set use_surrogate.

method,
 mesh_adaptive_search
 model_pointer = 'SURROGATE'
 use_surrogate inform_search

model,
 id_model = 'SURROGATE'
 surrogate global
 polynomial quadratic
 dace_method_pointer = 'SAMPLING'

variables,
 continuous_design = 3
   initial_point   -1.0    1.5   2.0
   upper_bounds    10.0   10.0  10.0
   lower_bounds   -10.0  -10.0 -10.0
   descriptors      'x1'  'x2'  'x3'
 discrete_design_range = 2
   initial_point      2     2
   lower_bounds       1     1
   upper_bounds       4     9
   descriptors      'y1'   'y2'
       discrete_design_set
         real = 2
           elements_per_variable = 4 5
           elements = 1.2 2.3 3.4 4.5 1.2 3.3 4.4 5.5 7.7
           descriptors      'y3'   'y4'
         integer = 2
           elements_per_variable = 2 2
           elements = 4 7 8 9
           descriptors      'z1'   'z2'

method,
 id_method = 'SAMPLING'
 model_pointer = 'TRUTH'
 sampling
   samples = 55

model,
 id_model = 'TRUTH'
 single
   interface_pointer = 'TRUE_FN'

interface,
 id_interface = 'TRUE_FN'
       direct
   analysis_driver = 'text_book'

responses,
 objective_functions = 1
 no_gradients
 no_hessians