Dakota 6.16

Highlight: Multifidelity UQ Methods

Dakota 6.16 significantly extends capabilities for multifidelity uncertainty quantification (MF UQ) based on random sampling, including iterated versions of approximate control variate (ACV) and multifidelity Monte Carlo (MFMC), new solution modes (online pilot, offline pilot, and pilot projection), new final statistics goals supporting estimator selection and tuning, online cost recovery through metadata, and improved numerical solution options for MFMC and ACV.

Documentation: Refer to Reference Manual documentation on MF UQ methods, in particular multilevel_sampling, multifidelity_sampling, multilevel_multifidelity_sampling, and approximate_control_variate.

Highlight: Model Tuning for Multifidelity UQ

New capabilities for model tuning enable the optimization of hyper-parameters underlying low-fidelity approximations in order to achieve the best accuracy versus cost trade-off for a given multifidelity estimator.

Documentation: This involves configuration of an outer optimization with a nested model, which in turn employs an MF UQ method.  Refer to the Nested Model documentation (Reference and Users) and the test examples in the source distribution at dakota/test/dakota_nested_tunable_acv.in.

See the release notes for further details.