Robust surrogate model

[uremes]

Summary:

This update adds a surrogate model version that can handle numerical errors observed as nan or inf values in the discrepancies between observed and simulated data. This is implemented as a new model class RobustGPyRegression. The two main differences between this and standard GPyRegression are that this version (1) does not use evidence points with non-finite output value to update the regression model and (2) can train a GPy classifier to predict whether given input parameters result in a finite output value or not. These capabilities are demonstrated here.

The new model can be combined with the unreliable simulations wrapper #484 to handle failed simulations in BOLFI as discussed in #433.

Please make sure

• You have read contribution guidelines
• You have updated CHANGELOG.rst
• You have listed the copyright holder for the work you are submitting (see next section)

If your contribution adds, removes or somehow changes the functional behavior of the package, please check that

• You have included or updated all the relevant documentation, including docstrings
• You have added appropriate functional and unit tests to ensure the new features behave as expected
• You have run make lint, make docs and make test

and the proposed changes pass all unit tests (check step 6 of CONTRIBUTING.rst for details)

Copyright and Licensing

Please list the copyright holder for the work you are submitting (this will be you or your assignee, such as a university or company):

By submitting this pull request, the copyright holder is agreeing to license the submitted work under the following licenses:

• Code: BSD3 (https://opensource.org/licenses/BSD-3-Clause)
• Documentation: CC-BY 4.0 (https://creativecommons.org/licenses/by/4.0/)