Regret Analysis of Posterior Sampling-Based Expected Improvement for Bayesian Optimization

Abstract

Bayesian optimization is a powerful tool for optimizing an expensive-to-evaluate black-box function. In particular, the effectiveness of expected improvement (EI) has been demonstrated in a wide range of applications. However, theoretical analyses of EI are limited compared with other theoretically established algorithms. This paper analyzes a randomized variant of EI, which evaluates the EI from the maximum of the posterior sample path. We show that this posterior sampling-based random EI achieves the sublinear Bayesian cumulative regret bounds under the assumption that the black-box function follows a Gaussian process. Finally, we demonstrate the effectiveness of the proposed method through numerical experiments.

Cite

Text

Takeno et al. "Regret Analysis of Posterior Sampling-Based Expected Improvement for Bayesian Optimization." Transactions on Machine Learning Research, 2025.

Markdown

[Takeno et al. "Regret Analysis of Posterior Sampling-Based Expected Improvement for Bayesian Optimization." Transactions on Machine Learning Research, 2025.](https://mlanthology.org/tmlr/2025/takeno2025tmlr-regret/)

BibTeX

@article{takeno2025tmlr-regret,
  title     = {{Regret Analysis of Posterior Sampling-Based Expected Improvement for Bayesian Optimization}},
  author    = {Takeno, Shion and Inatsu, Yu and Karasuyama, Masayuki and Takeuchi, Ichiro},
  journal   = {Transactions on Machine Learning Research},
  year      = {2025},
  url       = {https://mlanthology.org/tmlr/2025/takeno2025tmlr-regret/}
}