Multi-Objective Hyperparameter Optimization in Machine Learning -- An Overview
It is an incremental survey that aims to educate practitioners on multi-objective hyperparameter optimization to improve applied ML workflows.
This paper addresses the problem of hyperparameter optimization in machine learning, which often focuses solely on predictive accuracy, by providing an overview of multi-objective approaches that consider additional metrics like fairness and robustness, but does not present new experimental results or concrete numbers.
Hyperparameter optimization constitutes a large part of typical modern machine learning workflows. This arises from the fact that machine learning methods and corresponding preprocessing steps often only yield optimal performance when hyperparameters are properly tuned. But in many applications, we are not only interested in optimizing ML pipelines solely for predictive accuracy; additional metrics or constraints must be considered when determining an optimal configuration, resulting in a multi-objective optimization problem. This is often neglected in practice, due to a lack of knowledge and readily available software implementations for multi-objective hyperparameter optimization. In this work, we introduce the reader to the basics of multi-objective hyperparameter optimization and motivate its usefulness in applied ML. Furthermore, we provide an extensive survey of existing optimization strategies, both from the domain of evolutionary algorithms and Bayesian optimization. We illustrate the utility of MOO in several specific ML applications, considering objectives such as operating conditions, prediction time, sparseness, fairness, interpretability and robustness.