arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2501.19342cs.LG
收藏

使用贝叶斯优化以少量解覆盖多个目标

Covering Multiple Objectives with a Small Set of Solutions Using Bayesian Optimization

University of Pennsylvania(宾夕法尼亚大学)

Natalie Maus, Kyurae Kim, Yimeng Zeng, Haydn Thomas Jones, Fangping Wan, Marcelo Der Torossian Torres, Cesar de la Fuente-Nunez, Jacob R. Gardner

AI总结:

针对多目标黑箱优化中覆盖优化问题,提出MOCOBO算法,通过新采集函数用少量解覆盖所有目标,实验证明其覆盖率接近单独优化,并在药物发现中展现潜力。

摘要:

在多目标黑箱优化中,目标通常是找到同时优化一组$T$个黑箱目标函数$f_1, \ldots, f_T$的解。传统方法通常寻求一个平衡所有目标间权衡的单一帕累托最优集。相比之下,我们考虑一个偏离此范式的问题设置:找到一组数量为$K < T$的小型解集,这些解共同“覆盖”这$T$个目标。如果对于每个目标$f_1, \ldots, f_T$,至少存在一个良好解,则定义该解集为“覆盖”。此问题设置的一个激励示例出现在药物设计中。例如,我们可能有$T$种病原体,旨在识别一组$K < T$种抗生素,使得每种病原体至少有一种抗生素可用于治疗。此问题称为覆盖优化,尚未通过贝叶斯优化(BO)框架解决。为填补此空白,我们开发了多目标覆盖贝叶斯优化(MOCOBO),一种用于解决覆盖优化的BO算法。我们的方法基于一种新的采集函数,类似于原始BO设置中的期望改进。我们在高维黑箱优化任务上展示了我们方法的性能,包括肽和分子设计中的应用。结果表明,MOCOBO找到的$K < T$个解的覆盖率匹配或几乎匹配通过单独优化每个目标获得的$T$个解的覆盖率。此外,在体外实验中,MOCOBO找到的肽对耐药病原体表现出高效力,进一步展示了MOCOBO在药物发现中的潜力。我们所有代码公开可用,链接如下:https://github.com/nataliemaus/mocobo。

英文摘要:

In multi-objective black-box optimization, the goal is typically to find solutions that optimize a set of $T$ black-box objective functions, $f_1, \ldots f_T$, simultaneously. Traditional approaches often seek a single Pareto-optimal set that balances trade-offs among all objectives. In contrast, we consider a problem setting that departs from this paradigm: finding a small set of $K < T$ solutions, that collectively "cover" the $T$ objectives. A set of solutions is defined as "covering" if, for each objective $f_1, \ldots f_T$, there is at least one good solution. A motivating example for this problem setting occurs in drug design. For example, we may have $T$ pathogens and aim to identify a set of $K < T$ antibiotics such that at least one antibiotic can be used to treat each pathogen. This problem, known as coverage optimization, has yet to be tackled with the Bayesian optimization (BO) framework. To fill this void, we develop Multi-Objective Coverage Bayesian Optimization (MOCOBO), a BO algorithm for solving coverage optimization. Our approach is based on a new acquisition function reminiscent of expected improvement in the vanilla BO setup. We demonstrate the performance of our method on high-dimensional black-box optimization tasks, including applications in peptide and molecular design. Results show that the coverage of the $K < T$ solutions found by MOCOBO matches or nearly matches the coverage of $T$ solutions obtained by optimizing each objective individually. Furthermore, in in vitro experiments, the peptides found by MOCOBO exhibited high potency against drug-resistant pathogens, further demonstrating the potential of MOCOBO for drug discovery. All of our code is publicly available at the following link: https://github.com/nataliemaus/mocobo.

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。

↑