arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.09262stat.MLcs.LGmath.OC
收藏

带期望改进的噪声贝叶斯优化的收敛速率研究

On the convergence rate of noisy Bayesian Optimization with Expected Improvement

Center for Applied Scientific Computing, Lawrence Livermore National Laboratory(劳伦斯利弗莫尔国家实验室应用科学计算中心);National University of Singapore(新加坡国立大学)

Jingyi Wang, Haowei Wang, Nai-Yuan Chiang, Cosmin G. Petra

AI总结:

针对贝叶斯优化中期望改进(EI)的理论收敛问题,本文在高斯过程(GP)先验假设下,首次建立带噪声观测的GP-EI渐近误差界及速率,并通过分析EI函数的探索利用性质,改进了无噪声和有噪声场景下的误差界。

摘要:

期望改进(EI)是贝叶斯优化(BO)中应用最广泛的获取函数之一。尽管数十年来它在应用中已被证明是成功的,但关于EI的理论收敛行为和速率仍存在重要的开放性问题。本文在三个新颖且关键的领域为EI的收敛理论做出了贡献。首先,我们考虑符合高斯过程(GP)先验假设的目标函数,而现有工作大多集中于再生核希尔伯特空间(RKHS)中的函数。其次,我们首次在GP先验假设下,为带有噪声观测的GP-EI建立了渐近误差界及其对应的速率。第三,通过研究非凸EI函数的探索与利用性质,我们为无噪声和有噪声两种情况建立了改进的GP-EI误差界。

英文摘要:

Expected improvement (EI) is one of the most widely used acquisition functions in Bayesian optimization (BO). Despite its proven success in applications for decades, important open questions remain on the theoretical convergence behaviors and rates for EI. In this paper, we contribute to the convergence theory of EI in three novel and critical areas. First, we consider objective functions that fit under the Gaussian process (GP) prior assumption, whereas existing works mostly focus on functions in the reproducing kernel Hilbert space (RKHS). Second, we establish for the first time the asymptotic error bound and its corresponding rate for GP-EI with noisy observations under the GP prior assumption. Third, by investigating the exploration and exploitation properties of the non-convex EI function, we establish improved error bounds of GP-EI for both the noise-free and noisy cases.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑