mlrMBO: A Modular Framework for Model-Based Optimization of Expensive Black-Box Functions

TL;DR

mlrMBO is a versatile R package for Bayesian optimization of expensive black-box functions, supporting various parameter types and offering modular components for customization.

Contribution

It introduces a modular, flexible framework for model-based optimization in R, enabling easy integration of different surrogate models and optimization strategies.

Findings

Demonstrates state-of-the-art performance on benchmark problems.

Supports multi-objective and mixed parameter optimization.

Offers extensive features like parallelization and visualization.

Abstract

We present mlrMBO, a flexible and comprehensive R toolbox for model-based optimization (MBO), also known as Bayesian optimization, which addresses the problem of expensive black-box optimization by approximating the given objective function through a surrogate regression model. It is designed for both single- and multi-objective optimization with mixed continuous, categorical and conditional parameters. Additional features include multi-point batch proposal, parallelization, visualization, logging and error-handling. mlrMBO is implemented in a modular fashion, such that single components can be easily replaced or adapted by the user for specific use cases, e.g., any regression learner from the mlr toolbox for machine learning can be used, and infill criteria and infill optimizers are easily exchangeable. We empirically demonstrate that mlrMBO provides state-of-the-art performance by comparing it on different benchmark scenarios against a wide range of other optimizers, including DiceOptim, rBayesianOptimization, SPOT, SMAC, Spearmint, and Hyperopt.