Abstract: Bayesian optimization (BO) is a widely popular approach for the hyperparameter optimization (HPO) in machine learning. At its core, BO iteratively evaluates promising configurations until a user-defined budget, such as wall-clock time or number of iterations, is exhausted. While the final performance after tuning heavily depends on the provided budget, it is hard to pre-specify an optimal value in advance. In this work, we propose an effective and intuitive termination criterion for BO that automatically stops the procedure if it is sufficiently close to the global optimum. Our key insight is that the discrepancy between the true objective (predictive performance on test data) and the computable target (validation performance) suggests stopping once the suboptimality in optimizing the target is dominated by the statistical estimation error. Across an extensive range of real-world HPO problems and baselines, we show that our termination criterion achieves a better trade-off between the test performance and optimization time. Additionally, we find that overfitting may occur in the context of HPO, which is arguably an overlooked problem in the literature, and show how our termination criterion helps to mitigate this phenomenon on both small and large datasets.
Keywords: Bayesian Optimization, Hyperparameter optimization, AutoML
One-sentence Summary: An effective and intuitive termination criterion for BO that automatically stops the HPO if it is sufficiently close to the global optima.
Track: Main track
Reproducibility Checklist: Yes
Broader Impact Statement: Yes
Paper Availability And License: Yes
Code Of Conduct: Yes
Reviewers: Aaron Klein email@example.com Huibin Shen firstname.lastname@example.org
Main Paper And Supplementary Material: pdf
CPU Hours: 0
GPU Hours: 0
TPU Hours: 0