.. _model-global_surrogate-dace_method_pointer-auto_refinement: """"""""""""""" auto_refinement """"""""""""""" Experimental auto-refinement of surrogate model **Topics** :ref:`surrogate_models ` .. toctree:: :hidden: :maxdepth: 1 model-global_surrogate-dace_method_pointer-auto_refinement-max_iterations model-global_surrogate-dace_method_pointer-auto_refinement-max_function_evaluations model-global_surrogate-dace_method_pointer-auto_refinement-convergence_tolerance model-global_surrogate-dace_method_pointer-auto_refinement-soft_convergence_limit model-global_surrogate-dace_method_pointer-auto_refinement-cross_validation_metric **Specification** - *Alias:* None - *Arguments:* None - *JSON argument key:* None **Child Keywords:** +-------------------------+------------------------+--------------------+--------------------------------+------------------------------------------------------------+ | Required/Optional | Description of Group | JSON Group Key | Dakota Keyword | Dakota Keyword Description | +=========================+========================+====================+================================+============================================================+ | 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-global_surrogate-dace_method_pointer-auto_refinement-max_iterations.html __ model-global_surrogate-dace_method_pointer-auto_refinement-max_function_evaluations.html __ model-global_surrogate-dace_method_pointer-auto_refinement-convergence_tolerance.html __ model-global_surrogate-dace_method_pointer-auto_refinement-soft_convergence_limit.html __ model-global_surrogate-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.