Bayesian Optimization and Model-Based Optimization of Expensive Black-Box Functions
Error handling for mlrMBO
Perform an mbo run on a test function and and visualize what happens.
Perform an MBO run on a multi-objective test function and and visualiz...
Finalizes the SMBO Optimization
Helper function which returns the (estimated) global optimum.
Get properties of MBO infill criterion.
Get names of supported infill-criteria optimizers.
Get names of supported multi-point infill-criteria optimizers.
Infill criteria.
Initialize an MBO infill criterion.
Initialize a manual sequential MBO run.
Set MBO options.
Generate default learner.
Create a transformation function for MBOExampleRun.
Optimizes a function with sequential model based optimization.
OptPath in mlrMBO
Parallelization in mlrMBO
Continues an mbo run from a save-file.
Finalizes an mbo run from a save-file.
Create an infill criterion.
Multi-Objective result object.
Single-Objective result object.
mlrMBO examples
OptProblem object.
OptResult object.
OptState object.
Generate ggplot2 Object
Renders plots for exampleRun objects and displays them.
MBO Result Plotting
Print mbo control object.
Propose candidates for the objective function
Renders plots for exampleRun objects, either in 1D or 2D, or exampleRu...
Extends mbo control object with infill criteria and infill optimizer o...
Set multi-objective options.
Set multipoint proposal options.
Set termination options.
Transformation methods.
Updates SMBO with the new observations
Flexible and comprehensive R toolbox for model-based optimization ('MBO'), also known as Bayesian optimization. It implements the Efficient Global Optimization Algorithm and is designed for both single- and multi- objective optimization with mixed continuous, categorical and conditional parameters. The machine learning toolbox 'mlr' provide dozens of regression learners to model the performance of the target algorithm with respect to the parameter settings. It provides many different infill criteria to guide the search process. Additional features include multi-point batch proposal, parallel execution as well as visualization and sophisticated logging mechanisms, which is especially useful for teaching and understanding of algorithm behavior. 'mlrMBO' is implemented in a modular fashion, such that single components can be easily replaced or adapted by the user for specific use cases.