|国家预印本平台
首页|Regret Analysis of Posterior Sampling-Based Expected Improvement for Bayesian Optimization

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

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

来源:Arxiv_logoArxiv
英文摘要

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.

Shion Takeno、Yu Inatsu、Masayuki Karasuyama、Ichiro Takeuchi

计算技术、计算机技术

Shion Takeno,Yu Inatsu,Masayuki Karasuyama,Ichiro Takeuchi.Regret Analysis of Posterior Sampling-Based Expected Improvement for Bayesian Optimization[EB/OL].(2025-07-13)[2025-07-23].https://arxiv.org/abs/2507.09828.点此复制

评论