arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2405.02449stat.MLcond-mat.mtrl-scics.LGq-bio.BM
收藏

质量加权 Vendi 分数及其在多样化实验设计中的应用

Quality-Weighted Vendi Scores And Their Application To Diverse Experimental Design

Washington University in St. Louis(圣路易斯华盛顿大学);Princeton University(普林斯顿大学);Vertaix(维泰克斯(Vertaix))

Quan Nguyen, Adji Bousso Dieng

AI总结:

本文提出质量加权 Vendi 分数,将质量因素纳入多样性度量,用于解决药物发现、材料发现和强化学习中的实验设计问题,实现质量与多样性的灵活平衡,使有效发现数量较基线提升70%–170%。

摘要:

主动搜索和贝叶斯优化等实验设计技术广泛应用于自然科学领域的数据收集与发现。然而,现有技术往往倾向于对搜索空间进行利用而非探索,这导致它们陷入局部最优。这种“坍缩”问题阻碍了实验设计算法产出多样化的高质量数据。在本文中,我们扩展了 Vendi 分数——一类可解释的基于相似性的多样性度量——以纳入质量因素。随后,我们利用这些质量加权 Vendi 分数来解决跨多种应用的实验设计问题,包括药物发现、材料发现和强化学习。我们发现,质量加权 Vendi 分数使我们能够构建灵活平衡质量与多样性的实验设计策略,并最终汇集出丰富且多样的高性能数据点集合。与基线相比,我们的算法使有效发现的数量增加了 70%–170%。

英文摘要:

Experimental design techniques such as active search and Bayesian optimization are widely used in the natural sciences for data collection and discovery. However, existing techniques tend to favor exploitation over exploration of the search space, which causes them to get stuck in local optima. This ``collapse" problem prevents experimental design algorithms from yielding diverse high-quality data. In this paper, we extend the Vendi scores -- a family of interpretable similarity-based diversity metrics -- to account for quality. We then leverage these quality-weighted Vendi scores to tackle experimental design problems across various applications, including drug discovery, materials discovery, and reinforcement learning. We found that quality-weighted Vendi scores allow us to construct policies for experimental design that flexibly balance quality and diversity, and ultimately assemble rich and diverse sets of high-performing data points. Our algorithms led to a 70%-170% increase in the number of effective discoveries compared to baselines.

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。

↑