arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2302.00839cs.LGstat.MEstat.ML
收藏

具有保形成本控制的快速在线价值最大化预测集

Fast Online Value-Maximizing Prediction Sets with Conformal Cost Control

University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);Relativity(Relativity公司);Carle Illinois College of Medicine(卡尔伊利诺伊医学院)

Zhen Lin, Shubhendu Trivedi, Cao Xiao, Jimeng Sun

AI总结:

本文提出 FavMac 流程,结合任意多标签分类器,通过在线更新机制在严格保形成本控制下最大化预测集价值,并在医疗与合成数据实验中优于基线。

摘要:

许多现实世界中的多标签预测问题涉及集合值预测,这些预测必须满足下游使用所规定的特定要求。我们关注一个典型场景,其中这些分别编码“价值”和“成本”的要求相互竞争。例如,医院可能期望智能诊断系统尽可能多地捕获严重且通常共病的疾病(价值),同时严格控制错误预测(成本)。我们提出了一个名为 FavMac 的通用流程,用于在此类场景中最大化价值并控制成本。FavMac 可以与几乎任何多标签分类器结合,提供关于成本控制的无分布理论保证。此外,与以往工作不同,它通过精心设计的在线更新机制处理现实世界的大规模应用,这一机制本身也具有独立意义。我们在若干医疗任务和合成数据集上的实验支持了方法论和理论贡献——FavMac 在保持严格成本控制的同时,相比若干变体和基线提供了更高的价值。代码可在 https://github.com/zlin7/FavMac 获取。

英文摘要:

Many real-world multi-label prediction problems involve set-valued predictions that must satisfy specific requirements dictated by downstream usage. We focus on a typical scenario where such requirements, separately encoding $\textit{value}$ and $\textit{cost}$, compete with each other. For instance, a hospital might expect a smart diagnosis system to capture as many severe, often co-morbid, diseases as possible (the value), while maintaining strict control over incorrect predictions (the cost). We present a general pipeline, dubbed as FavMac, to maximize the value while controlling the cost in such scenarios. FavMac can be combined with almost any multi-label classifier, affording distribution-free theoretical guarantees on cost control. Moreover, unlike prior works, it can handle real-world large-scale applications via a carefully designed online update mechanism, which is of independent interest. Our methodological and theoretical contributions are supported by experiments on several healthcare tasks and synthetic datasets - FavMac furnishes higher value compared with several variants and baselines while maintaining strict cost control. Our code is available at https://github.com/zlin7/FavMac

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。

↑