arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.00890cs.LGmath.OCstat.ML
收藏

高维贝叶斯优化算法在BBOB上的比较

Comparison of High-Dimensional Bayesian Optimization Algorithms on BBOB

Sorbonne Université(索邦大学);CNRS(法国国家科学研究中心);Leiden University(莱顿大学);University of Camerino(卡梅里诺大学)

Maria Laura Santoni, Elena Raponi, Renato De Leone, Carola Doerr

AI总结:

本研究在COCO环境的24个BBOB函数的10-60维场景下,对比五种前沿高维BO算法与基础BO、CMA-ES的性能,证实有限预算下BO更优,指出信赖域是提升BO性能的最具前景方向,也发现不同场景下性能差异显著,存在混合改进空间。

摘要:

贝叶斯优化(BO)是一类基于代理模型的黑箱启发式算法,能够高效优化评估成本高昂、因此仅能承受少量评估预算的问题。BO在工业界求解数值优化问题时尤为流行,这类场景中目标函数的评估往往依赖耗时的仿真或物理实验。然而,许多工业问题依赖大量参数,这给BO算法带来了挑战——据报道,当维度超过15个变量时,BO算法的性能通常会下降。尽管已有许多新算法被提出以解决这一问题,但目前尚不清楚哪种算法最适合哪种优化场景。\n在本研究中,我们在COCO环境的24个BBOB函数上,针对10到60个变量的递增维度,将五种前沿高维BO算法与基础版BO以及CMA-ES进行了对比。我们的结果证实了在有限评估预算下BO优于CMA-ES,并表明提升BO性能最具前景的途径是使用信赖域。不过,我们也观察到不同函数景观和预算利用阶段下存在显著的性能差异,这显示出例如通过算法组件混合来改进的潜力。

英文摘要:

Bayesian Optimization (BO) is a class of black-box, surrogate-based heuristics that can efficiently optimize problems that are expensive to evaluate, and hence admit only small evaluation budgets. BO is particularly popular for solving numerical optimization problems in industry, where the evaluation of objective functions often relies on time-consuming simulations or physical experiments. However, many industrial problems depend on a large number of parameters. This poses a challenge for BO algorithms, whose performance is often reported to suffer when the dimension grows beyond 15 variables. Although many new algorithms have been proposed to address this problem, it is not well understood which one is the best for which optimization scenario. In this work, we compare five state-of-the-art high-dimensional BO algorithms, with vanilla BO and CMA-ES on the 24 BBOB functions of the COCO environment at increasing dimensionality, ranging from 10 to 60 variables. Our results confirm the superiority of BO over CMA-ES for limited evaluation budgets and suggest that the most promising approach to improve BO is the use of trust regions. However, we also observe significant performance differences for different function landscapes and budget exploitation phases, indicating improvement potential, e.g., through hybridization of algorithmic components.

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。

↑