.. _method-multilevel_blue: """"""""""""""" multilevel_blue """"""""""""""" The multilevel best linear unbiased estimator (ML BLUE) sampling method for UQ .. toctree:: :hidden: :maxdepth: 1 method-multilevel_blue-model_pointer method-multilevel_blue-rng method-multilevel_blue-max_function_evaluations method-multilevel_blue-max_iterations method-multilevel_blue-convergence_tolerance method-multilevel_blue-sample_type method-multilevel_blue-seed_sequence method-multilevel_blue-fixed_seed method-multilevel_blue-solver_metric method-multilevel_blue-sqp method-multilevel_blue-nip method-multilevel_blue-global_local method-multilevel_blue-competed_local method-multilevel_blue-solution_mode method-multilevel_blue-pilot_samples method-multilevel_blue-group_throttle method-multilevel_blue-id_method method-multilevel_blue-output method-multilevel_blue-final_solutions method-multilevel_blue-export_sample_sequence **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 | | | `rng`__ | Selection of a random number generator | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ | Optional | | | `max_function_evaluations`__ | Stopping criterion based on maximum function evaluations | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ | Optional | | | `max_iterations`__ | Number of iterations allowed for optimizers and adaptive | | | | | | UQ methods | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ | Optional | | | `convergence_tolerance`__ | Stopping criterion based on relative error reduction | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ | Optional | | | `sample_type`__ | Selection of sampling strategy | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ | Optional | | | `seed_sequence`__ | Sequence of seed values for multi-stage random sampling | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ | Optional | | | `fixed_seed`__ | Reuses the same seed value for multiple random sampling | | | | | | sets | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ | Optional | | | `solver_metric`__ | Metric employed during numerical solutions in | | | | | | sampling-based multifidelity UQ methods. | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ | Optional (Choose One) | Optimization Solver | optimization_solver | `sqp`__ | Use a sequential quadratic programming method for solving | | | | | | an optimization sub-problem | + + + +--------------------------------+------------------------------------------------------------+ | | | | `nip`__ | Use a nonlinear interior point method for solving an | | | | | | optimization sub-problem | + + + +--------------------------------+------------------------------------------------------------+ | | | | `global_local`__ | Use a hybrid global-local scheme for solving an | | | | | | optimization sub-problem | + + + +--------------------------------+------------------------------------------------------------+ | | | | `competed_local`__ | Use a competed local solver scheme for solving an | | | | | | optimization sub-problem | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ | Optional | | | `solution_mode`__ | Solution mode for multilevel/multifidelity methods | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ | Optional | | | `pilot_samples`__ | Initial set of samples for groups in the multilevel BLUE | | | | | | sampling method | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ | Optional | | | `group_throttle`__ | Reduce the number of groups in multilevel BLUE using a | | | | | | throttle | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ | 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 | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ | Optional | | | `export_sample_sequence`__ | Enable export of multilevel/multifidelity sample sequences | | | | | | to individual files | +-------------------------+------------------------+---------------------+--------------------------------+------------------------------------------------------------+ .. __: method-multilevel_blue-model_pointer.html __ method-multilevel_blue-rng.html __ method-multilevel_blue-max_function_evaluations.html __ method-multilevel_blue-max_iterations.html __ method-multilevel_blue-convergence_tolerance.html __ method-multilevel_blue-sample_type.html __ method-multilevel_blue-seed_sequence.html __ method-multilevel_blue-fixed_seed.html __ method-multilevel_blue-solver_metric.html __ method-multilevel_blue-sqp.html __ method-multilevel_blue-nip.html __ method-multilevel_blue-global_local.html __ method-multilevel_blue-competed_local.html __ method-multilevel_blue-solution_mode.html __ method-multilevel_blue-pilot_samples.html __ method-multilevel_blue-group_throttle.html __ method-multilevel_blue-id_method.html __ method-multilevel_blue-output.html __ method-multilevel_blue-final_solutions.html __ method-multilevel_blue-export_sample_sequence.html **Description** An adaptive multifidelity sampling method that improves performance relative to single-fidelity Monte Carlo sampling, either of terms of greater accuracy (reduced variance in the estimated statistics) for a prescribed budget or reduced cost for specified accuracy. It employs an ensemble model to manage a set of lower-fidelity approximations to a single truth model. Compared to other estimators (MLMC, MLCV MC, MFMC, ACV, generalized ACV), ML BLUE is distinguished in that it employs a group-based approach, where independent samples are allocated for each group and each group is composed of unordered combinations of models. The number of groups grows combinatorially with the total number of models, and a few throttle options are provided to prevent the number of groups from growing to excess. As described in :cite:p:`Schaden2020`, the ML BLUE estimator for QoI expected values is .. math:: \Psi q^B = y where .. math:: \Psi = \sum_{k=1}^K m_k R_k^T C_k^{-1} R_k .. math:: y = \sum_{k=1}^K R_k^T C_k^{-1} S_k .. math:: S_k = \sum_{i=1}^{m_k} Y_k^{(i)} given group sample count :math:`m_k`, group restriction operator :math:`R_k`, group covariance estimate :math:`C_k`, and group QoI sum :math:`S_k` for each group :math:`k`. For a linear combination of the model means :math:`q_{\beta}^B = \beta^T q^B`, the variance of ML BLUE is :math:`\beta^T \Psi^{-1} \beta`. The numerical solution for :math:`m` minimizes this variance subject to a prescribed budget (or minimizes cost for specified accuracy), where the common choice of :math:`\beta = [1, 0, 0, \dots]^T` targets the HF mean. **Status** This method is currently under active development. It exhibits competitive performance for smaller numbers of models (roughly 5 or less), whereas larger model ensembles lead to ill-conditioning in the matrix solutions and inaccurate results. Throttling can delay these problems in some cases, but more advanced numerical treatments are needed (work in progress). *Default Behavior* The ``multilevel_blue`` method employs a number of important default settings: * The pilot sampling strategy involves shared samples for initial estimation of group covariances (refer to :dakkw:`method-multilevel_blue-pilot_samples`). * The number of groups is not throttled by default (refer to :dakkw:`method-multilevel_blue-group_throttle`). * The default solver is ``global_local``, starting with the DIRECT global solver and proceeding to available local solvers (SQP and NIP) in competition. For larger group counts, a purely local approach can be more scalable. * Solution mode will be ``online_pilot``, an approach which iterates toward a set of shared samples whose size is consistent with the optimal allocation. Since group-based approaches will try to allocate the entire budget on the first iteration, the use of under-relaxation (see :dakkw:`method-multilevel_blue-solution_mode-online_pilot-relaxation`) can be especially beneficial. * Monte Carlo sample sets are used by default and are most consistent with the underlying theory, but this default can be overridden to use Latin hypercube sample sets using ``sample_type`` ``lhs``. Allocations remain governed by Monte Carlo variance for all cases. *Expected Output* The ``multilevel_blue`` method reports estimates of the first four moments and a summary of the evaluations performed for each group and for each model instance. The method does not support any level mappings (response, probability, reliability, generalized reliability) at this time. *Usage Tips* The ``multilevel_blue`` method must be used in combination with an ensemble model specification that enumerates a truth model and approximation models using either a model form ensemble, a set of resolution levels, or some combination. By default, all model forms and resolution levels will be enumerated within the model ensemble. For each model instance, cost data must by provided either using ``solution_level_cost`` or metadata that is returned from simulations for estimating cost on the fly. For a sequence of discretization levels, ``solution_level_control`` must identify the variable string descriptor that controls the resolution levels and the associated array of relative costs must be provided using ``solution_level_cost``. **Examples** The following method block: .. tab:: Freeform .. code-block:: dakota method model_pointer = 'HIERARCH' multilevel_blue pilot_samples = 25 seed = 8674132 max_function_evaluations = 500 model id_model = 'HIERARCH' ensemble_surrogate ordered_model_fidelities = 'HF' correction additive zeroth_order model id_model = 'HF' simulation solution_level_control = 'mesh_size' solution_level_cost = 1 16 256 .. tab:: JSON .. code-block:: json { "method": [ { "multilevel_blue": { "model_pointer": "HIERARCH", "pilot_samples": { "counts": [25] }, "seed_sequence": [8674132], "max_function_evaluations": 500 } } ], "model": [ { "ensemble_surrogate": { "id_model": "HIERARCH", "ensemble": { "ordered_model_fidelities": { "pointers": ["HF"], "correction": { "correction_type": {"additive": true}, "correction_order": {"zeroth_order": true} } } } } }, { "single": { "id_model": "HF", "cost_model": { "solution_level_cost": [1.0, 16.0, 256.0] } } } ] } specifies ML BLUE using an iterated online pilot in combination with the default optimization solver strategy (global_local), the default shared pilot estimation of group covariances, and an ensemble model identified by the HIERARCH pointer. This HIERARCH model specification provides a one-dimensional sequence, here defined by a set of 3 discretization levels. Refer to ``dakota/test/dakota_uq_diffusion_mlblue_cost4``.in within the source distribution for this case as well as additional examples. **Theory** Refer to :cite:p:`Schaden2020` for more detailed algorithm descriptions, theoretical considerations, and illustrative examples.