@inproceedings {pub5605,
	title = {Using Bayesian Optimization to Improve Hyperparameter Search in AutoML},
	author = {Angus Kenny AND Tapabrata Ray AND Steffen Limmer AND Hemant Kumar Singh AND Tobias Rodemann AND Markus Olhofer},
	year = {2024},
	month = {July},
	abstract = {Automated machine learning (AutoML) has emerged as a pivotal tool for applying machine learning (ML) models to real-world problems. Among the various AutoML tools, the tree-based pipeline optimization tool (TPOT) is known for effectively solving complex tasks. TPOT{\textquoteright}s search involves two fundamental objectives: finding optimal pipeline structures (i.e., combinations of ML operators) and identifying suitable hyperparameters for these structures. While its use of genetic programming enables TPOT to excel in structural search, its hyperparameter search, involving discretization and random selection from extensive potential value ranges, can be computationally inefficient.
This paper presents a novel methodology that heavily restricts the initial hyperparameter search space, directing TPOT{\textquoteright}s focus towards structural exploration. As the search evolves, Bayesian optimization (BO) is used to refine the hyperparameter space based on data from previous pipeline evaluations. This method leads to a more targeted search, crucial in situations with limited computational resources. Variants of this approach are proposed and compared with standard TPOT across six datasets, with up to 20 features and 20,000 samples. The results show the proposed method is competitive with canonical TPOT, outperforming it in several cases. The study also provides new insights into the dynamics of pipeline structure and hyperparameter search within TPOT.},
	publisher = {ACM},
	isbn = {9798400704949},
	url = {https://doi.org/10.1145/3638529.3654061},
	booktitle = {GECCO {\textquoteright}24: Proceedings of the Genetic and Evolutionary Computation Conference},
	pages = {340{\textendash}348}
}