.. _model-surrogate-global-dace_method_pointer-auto_refinement:

"""""""""""""""
auto_refinement
"""""""""""""""


Experimental auto-refinement of surrogate model



**Topics**


surrogate_models


.. toctree::
   :hidden:
   :maxdepth: 1

   model-surrogate-global-dace_method_pointer-auto_refinement-max_iterations
   model-surrogate-global-dace_method_pointer-auto_refinement-max_function_evaluations
   model-surrogate-global-dace_method_pointer-auto_refinement-convergence_tolerance
   model-surrogate-global-dace_method_pointer-auto_refinement-soft_convergence_limit
   model-surrogate-global-dace_method_pointer-auto_refinement-cross_validation_metric


**Specification**

- *Alias:* None

- *Arguments:* None

- *Default:* no refinement


**Child Keywords:**

+-------------------------+--------------------+------------------------------+-----------------------------------------------+
| Required/Optional       | Description of     | Dakota Keyword               | Dakota Keyword Description                    |
|                         | Group              |                              |                                               |
+=========================+====================+==============================+===============================================+
| Optional                                     | `max_iterations`__           | Number of iterations allowed for optimizers   |
|                                              |                              | and adaptive UQ methods                       |
+----------------------------------------------+------------------------------+-----------------------------------------------+
| Optional                                     | `max_function_evaluations`__ | Number of function evaluations allowed for    |
|                                              |                              | optimizers                                    |
+----------------------------------------------+------------------------------+-----------------------------------------------+
| Optional                                     | `convergence_tolerance`__    | Cross-validation threshold for surrogate      |
|                                              |                              | convergence                                   |
+----------------------------------------------+------------------------------+-----------------------------------------------+
| Optional                                     | `soft_convergence_limit`__   | Maximum number of iterations without          |
|                                              |                              | improvement in cross-validation               |
+----------------------------------------------+------------------------------+-----------------------------------------------+
| Optional                                     | `cross_validation_metric`__  | Choice of error metric to satisfy             |
+----------------------------------------------+------------------------------+-----------------------------------------------+

.. __: model-surrogate-global-dace_method_pointer-auto_refinement-max_iterations.html
__ model-surrogate-global-dace_method_pointer-auto_refinement-max_function_evaluations.html
__ model-surrogate-global-dace_method_pointer-auto_refinement-convergence_tolerance.html
__ model-surrogate-global-dace_method_pointer-auto_refinement-soft_convergence_limit.html
__ model-surrogate-global-dace_method_pointer-auto_refinement-cross_validation_metric.html



**Description**


(Experimental option) Automatically refine the surrogate model until
desired cross-validation quality is achieved. Refinement is accomplished
by iteratively adding more data to the training set until the cross-validation
``convergence_tolerance`` is achieved, or ``max_function_evaluations`` or
``max_iterations`` is exceeded.

The amount of new training data that is incorporated each iteration is specified
in the DACE method that is referred to by the model's ``dace_method_pointer``.
See :dakkw:`method-sampling-refinement_samples` for more information.