[论文] JAREX: An Acquisition Function for Multi-Objective Algorithmic Process...

论文概要

研究领域: ML 作者: Xinyang Li, Kevin Stone, Ajit Vikram 发布时间: 2026-09-21 arXiv: 2609.24954

中文摘要

药物工艺表征是质量源于设计（QbD）的核心，因为它定义了工艺参数的变化如何影响满足产品质量标准的能力，从而支持可接受范围证明和稳健制造。然而在实际中，工艺表征仍主要依赖析因实验设计（DOE）方法，这对于在高维空间中解析多变量通过/失败边界效率低下。贝叶斯优化已经改变了工艺优化，但多目标工艺表征的自适应方法仍然缺乏。我们提出 JAREX（联合可接受区域探索），一种用于多目标工艺表征的贝叶斯主动学习采集函数。JAREX 将表征建模为联合边界学习问题，自适应选择实验以恢复由多个目标同时满足阈值标准定义的联合通过区域。JAREX 结合了乐观的联合可行性掩码和随机跨越的多目标扩展，将采样集中于联合失败边缘。基准研究表明，在完整实验预算范围内，JAREX 比析因 DOE、空间填充设计和贪心逐目标策略更准确地恢复联合通过区域且样本效率更高。对于批量实验，它将迭代工艺表征实验的数量减少了一半以上，同时保持了边界识别任务的高精度。JAREX 已在开源 obsidian 包中实现，为自适应、数据高效的多目标算法化工艺表征提供了模块化框架。

原文摘要

Pharmaceutical process characterization is central to Quality by Design because it defines how variations in process parameters affect the ability to meet product quality specifications, thereby supporting proven acceptable ranges and robust manufacturing. In practice, however, characterization still relies largely on factorial design of experiments (DOE) approaches, which are inefficient for resolving multivariate pass/fail boundaries in higher-dimensional spaces. While Bayesian optimization has transformed process optimization, adaptive methods for multi-objective process characterization remain lacking. Here, we introduce JAREX (Joint Acceptable Region EXploration), a Bayesian active-learning acquisition function for multi-objective process characterization. JAREX formulates characteriz...

#论文 #arXiv #ML #小凯