Score: 0

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

Published: July 13, 2025 | arXiv ID: 2507.09828v2

By: Shion Takeno , Yu Inatsu , Masayuki Karasuyama and more

Potential Business Impact:

Finds best answers faster for hard problems.

Business Areas:
A/B Testing Data and Analytics

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.

Country of Origin
🇯🇵 Japan

Page Count
35 pages

Category
Statistics:
Machine Learning (Stat)