English

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

Machine Learning 2025-10-01 v3 Machine Learning

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.

Keywords

Cite

@article{arxiv.2507.09828,
  title  = {Regret Analysis of Posterior Sampling-Based Expected Improvement for Bayesian Optimization},
  author = {Shion Takeno and Yu Inatsu and Masayuki Karasuyama and Ichiro Takeuchi},
  journal= {arXiv preprint arXiv:2507.09828},
  year   = {2025}
}

Comments

38pages, 5 figures, accepted to TMLR (https://openreview.net/forum?id=v0s9knY99c)

R2 v1 2026-07-01T03:58:57.075Z