Flexible Bayesian Optimization
Syntactic Sugar Acquisition Function Construction
Syntactic Sugar Acquisition Functions Construction
Acquisition Function Base Class
Syntactic Sugar Acquisition Function Optimizer Construction
Acquisition Function Optimizer
Default Acquisition Function
Default Acquisition Function Optimizer
Default Gaussian Process
Default Loop Function
Default Result Assigner
Default Random Forest
Default Surrogate
Input Transformation Base Class
Input Transformation Unitcube
Syntactic Sugar Input Trafo Construction
Loop Functions for Bayesian Optimization
Defaults for OptimizerMbo
Acquisition Function Augmented Expected Improvement
Acquisition Function Confidence Bound
Acquisition Function Expected Hypervolume Improvement
Acquisition Function Expected Hypervolume Improvement via Gauss-Hermit...
Acquisition Function Expected Improvement on Log Scale
Acquisition Function Expected Improvement
Acquisition Function Expected Improvement Per Second
Acquisition Function Mean
Acquisition Function Wrapping Multiple Acquisition Functions
Acquisition Function Probability of Improvement
Acquisition Function Standard Deviation
Acquisition Function SMS-EGO
Acquisition Function Stochastic Confidence Bound
Acquisition Function Stochastic Expected Improvement
Dictionary of Acquisition Functions
Dictionary of Input Transformations
Sequential Single-Objective Bayesian Optimization
Sequential Multi-Objective Bayesian Optimization
Single-Objective Bayesian Optimization via Multipoint Constant Liar
Multi-Objective Bayesian Optimization via ParEGO
Sequential Multi-Objective Bayesian Optimization via SMS-EGO
Dictionary of Loop Functions
Asynchronous Decentralized Bayesian Optimization
Asynchronous Model Based Optimization
Model Based Optimization
Dictionary of Output Transformations
Result Assigner Based on the Archive
Result Assigner Based on a Surrogate Mean Prediction
Dictionary of Result Assigners
TunerAsync using Asynchronous Decentralized Bayesian Optimization
TunerAsync using Asynchronous Model Based Optimization
TunerBatch using Model Based Optimization
mlr3mbo: Flexible Bayesian Optimization
Syntactic Sugar Output Trafo Construction
Output Transformation Base Class
Output Transformation Log
Output Transformation Standardization
Syntactic Sugar Result Assigner Construction
Check if Redis Server is Available
Result Assigner Base Class
Syntactic Sugar Surrogate Construction
Surrogate Model
Surrogate Model Containing a Single Learner
Surrogate Model Containing Multiple Learners
A modern and flexible approach to Bayesian Optimization / Model Based Optimization building on the 'bbotk' package. 'mlr3mbo' is a toolbox providing both ready-to-use optimization algorithms as well as their fundamental building blocks allowing for straightforward implementation of custom algorithms. Single- and multi-objective optimization is supported as well as mixed continuous, categorical and conditional search spaces. Moreover, using 'mlr3mbo' for hyperparameter optimization of machine learning models within the 'mlr3' ecosystem is straightforward via 'mlr3tuning'. Examples of ready-to-use optimization algorithms include Efficient Global Optimization by Jones et al. (1998) <doi:10.1023/A:1008306431147>, ParEGO by Knowles (2006) <doi:10.1109/TEVC.2005.851274> and SMS-EGO by Ponweiser et al. (2008) <doi:10.1007/978-3-540-87700-4_78>.
Useful links