.. _method-function_train: """""""""""""" function_train """""""""""""" UQ method leveraging a functional tensor train surrogate model. .. toctree:: :hidden: :maxdepth: 1 method-function_train-model_pointer method-function_train-seed method-function_train-fixed_seed method-function_train-samples_on_emulator method-function_train-sample_type method-function_train-rng method-function_train-probability_refinement method-function_train-final_moments method-function_train-response_levels method-function_train-probability_levels method-function_train-reliability_levels method-function_train-gen_reliability_levels method-function_train-distribution method-function_train-variance_based_decomp method-function_train-import_approx_points_file method-function_train-export_approx_points_file method-function_train-diagonal_covariance method-function_train-full_covariance method-function_train-start_rank method-function_train-adapt_rank method-function_train-kick_rank method-function_train-max_rank method-function_train-max_cv_rank_candidates method-function_train-start_order method-function_train-adapt_order method-function_train-kick_order method-function_train-max_order method-function_train-max_cv_order_candidates method-function_train-rounding_tolerance method-function_train-arithmetic_tolerance method-function_train-regression_type method-function_train-max_solver_iterations method-function_train-max_cross_iterations method-function_train-solver_tolerance method-function_train-response_scaling method-function_train-tensor_grid method-function_train-collocation_points method-function_train-collocation_ratio method-function_train-refinement_metric method-function_train-convergence_tolerance method-function_train-p_refinement method-function_train-max_refinement_iterations method-function_train-id_method method-function_train-output method-function_train-final_solutions **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 | | | `model_pointer`__ | Identifier for model block to be used by a method | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ | Optional | | | `seed`__ | Seed of the random number generator | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ | Optional | | | `fixed_seed`__ | Reuses the same seed value for multiple random sampling | | | | | | sets | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ | Optional | | | `samples_on_emulator`__ | Number of samples at which to evaluate an emulator | | | | | | (surrogate) | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ | Optional | | | `sample_type`__ | Selection of sampling strategy | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ | Optional | | | `rng`__ | Selection of a random number generator | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ | Optional | | | `probability_refinement`__ | Allow refinement of probability and generalized | | | | | | reliability results using importance sampling | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ | Optional | | | `final_moments`__ | Output moments of the specified type and include them | | | | | | within the set of final statistics. | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ | Optional | | | `response_levels`__ | Values at which to estimate desired statistics for each | | | | | | response | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ | Optional | | | `probability_levels`__ | Specify probability levels at which to estimate the | | | | | | corresponding response value | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ | Optional | | | `reliability_levels`__ | Specify reliability levels at which the response values | | | | | | will be estimated | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ | Optional | | | `gen_reliability_levels`__ | Specify generalized relability levels at which to estimate | | | | | | the corresponding response value | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ | Optional | | | `distribution`__ | Selection of cumulative or complementary cumulative | | | | | | functions | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ | Optional | | | `variance_based_decomp`__ | Activates global sensitivity analysis based on | | | | | | decomposition of response variance into main, interaction, | | | | | | and total effects | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ | Optional | | | `import_approx_points_file`__ | Filename for points at which to evaluate the PCE/SC | | | | | | surrogate | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ | Optional | | | `export_approx_points_file`__ | Output file for surrogate model value evaluations | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ | Optional (Choose One) | Covariance Type | covariance_type | `diagonal_covariance`__ | Display only the diagonal terms of the covariance matrix | + + + +--------------------------------+------------------------------------------------------------+ | | | | `full_covariance`__ | Display the full covariance matrix | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ | Optional | | | `start_rank`__ | The initial rank used for the starting point during a rank | | | | | | adaptation. | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ | Optional | | | `adapt_rank`__ | Activate adaptive procedure for determining best rank | | | | | | representation | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ | Optional | | | `kick_rank`__ | The increment in rank employed during each iteration of | | | | | | the rank adaptation. | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ | Optional | | | `max_rank`__ | Limits the maximum rank that is explored during a rank | | | | | | adaptation. | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ | Optional | | | `max_cv_rank_candidates`__ | Limit the number of cross-validation candidates for rank | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ | Optional | | | `start_order`__ | (Initial) polynomial order of each univariate function | | | | | | within the functional tensor train. | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ | Optional | | | `adapt_order`__ | Activate adaptive procedure for determining the best basis | | | | | | order | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ | Optional | | | `kick_order`__ | increment used when adapting the basis order in function | | | | | | train methods | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ | Optional | | | `max_order`__ | Maximum polynomial order of each univariate function | | | | | | within the functional tensor train. | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ | Optional | | | `max_cv_order_candidates`__ | Limit the number of cross-validation candidates for basis | | | | | | order | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ | Optional | | | `rounding_tolerance`__ | An accuracy tolerance that is used to guide rounding | | | | | | during rank adaptation. | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ | Optional | | | `arithmetic_tolerance`__ | A secondary rounding tolerance used for post-processing | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ | Optional | | | `regression_type`__ | Type of solver for forming function train approximations | | | | | | by regression | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ | Optional | | | `max_solver_iterations`__ | Maximum iterations in determining polynomial coefficients | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ | Optional | | | `max_cross_iterations`__ | Maximum number of iterations for cross-approximation | | | | | | during a rank adaptation. | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ | Optional | | | `solver_tolerance`__ | Convergence tolerance for the optimizer used during the | | | | | | regression solve. | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ | Optional | | | `response_scaling`__ | Perform bounds-scaling on response values prior to | | | | | | surrogate emulation | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ | Optional | | | `tensor_grid`__ | Use sub-sampled tensor-product quadrature points to build | | | | | | a polynomial chaos expansion. | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ | Required (Choose One) | Collocation Control | collocation_control | `collocation_points`__ | Number of collocation points used to estimate expansion | | | | | | coefficients | + + + +--------------------------------+------------------------------------------------------------+ | | | | `collocation_ratio`__ | Set the number of points used to build a PCE via | | | | | | regression to be proportional to the number of terms in | | | | | | the expansion. | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ | Optional | | | `refinement_metric`__ | Metric used for guiding adaptive refinement during UQ. | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ | Optional | | | `convergence_tolerance`__ | Stopping criterion based on objective function or | | | | | | statistics convergence | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ | Optional | | | `p_refinement`__ | Automatic polynomial order refinement | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ | Optional | | | `max_refinement_iterations`__ | Maximum number of expansion refinement iterations | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ | Optional | | | `id_method`__ | Name the method block; helpful when there are multiple | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ | Optional | | | `output`__ | Control how much method information is written to the | | | | | | screen and output file | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ | Optional | | | `final_solutions`__ | Number of designs returned as the best solutions | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ .. __: method-function_train-model_pointer.html __ method-function_train-seed.html __ method-function_train-fixed_seed.html __ method-function_train-samples_on_emulator.html __ method-function_train-sample_type.html __ method-function_train-rng.html __ method-function_train-probability_refinement.html __ method-function_train-final_moments.html __ method-function_train-response_levels.html __ method-function_train-probability_levels.html __ method-function_train-reliability_levels.html __ method-function_train-gen_reliability_levels.html __ method-function_train-distribution.html __ method-function_train-variance_based_decomp.html __ method-function_train-import_approx_points_file.html __ method-function_train-export_approx_points_file.html __ method-function_train-diagonal_covariance.html __ method-function_train-full_covariance.html __ method-function_train-start_rank.html __ method-function_train-adapt_rank.html __ method-function_train-kick_rank.html __ method-function_train-max_rank.html __ method-function_train-max_cv_rank_candidates.html __ method-function_train-start_order.html __ method-function_train-adapt_order.html __ method-function_train-kick_order.html __ method-function_train-max_order.html __ method-function_train-max_cv_order_candidates.html __ method-function_train-rounding_tolerance.html __ method-function_train-arithmetic_tolerance.html __ method-function_train-regression_type.html __ method-function_train-max_solver_iterations.html __ method-function_train-max_cross_iterations.html __ method-function_train-solver_tolerance.html __ method-function_train-response_scaling.html __ method-function_train-tensor_grid.html __ method-function_train-collocation_points.html __ method-function_train-collocation_ratio.html __ method-function_train-refinement_metric.html __ method-function_train-convergence_tolerance.html __ method-function_train-p_refinement.html __ method-function_train-max_refinement_iterations.html __ method-function_train-id_method.html __ method-function_train-output.html __ method-function_train-final_solutions.html **Description** Tensor train decompositions are approximations that exploit low rank structure in an input-output mapping. Refer to the :dakkw:`model-global_surrogate-function_train` surrogate model for additional details. *Usage Tips* This method is a self-contained method alternative to the :dakkw:`model-global_surrogate-function_train` surrogate model specification, similar to current method specifications for polynomial chaos and stochastic collocation. In particular, this ``function_train`` method specification directly couples with a simulation model (optionally identified with a ``model_pointer``) and an additional ``function`` train surrogate model specification is not required as these options have been embedded within the method specification. **Examples** .. tab:: Freeform .. code-block:: dakota method function_train start_order = 2 start_rank = 2 kick_rank = 2 max_rank = 10 adapt_rank solver_tolerance = 1e-12 rounding_tolerance = 1e-12 convergence_tol = 1e-6 collocation_points = 100 samples_on_emulator = 100000 seed = 531 response_levels = .1 1. 50. 100. 500. 1000. variance_based_decomp .. tab:: JSON .. code-block:: json { "method": [ { "function_train": { "start_order": { "value": 2 }, "start_rank": 2, "kick_rank": 2, "max_rank": 10, "adapt_rank": true, "solver_tolerance": 1e-12, "rounding_tolerance": 1e-12, "collocation_control": { "collocation_points": 100 }, "samples_on_emulator": 100000, "seed": 531 } } ] }