English

Automatic Termination for Hyperparameter Optimization

Machine Learning 2022-07-25 v4 Artificial Intelligence Machine Learning

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

Cite

@article{arxiv.2104.08166,
  title  = {Automatic Termination for Hyperparameter Optimization},
  author = {Anastasia Makarova and Huibin Shen and Valerio Perrone and Aaron Klein and Jean Baptiste Faddoul and Andreas Krause and Matthias Seeger and Cedric Archambeau},
  journal= {arXiv preprint arXiv:2104.08166},
  year   = {2022}
}

Comments

Accepted at AutoML Conference 2022