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 2309.00645stat.MLcs.LGmath.PR
收藏

诊断分析(第一部分):患病率、不确定性量化与机器学习

Analysis of Diagnostics (Part I): Prevalence, Uncertainty Quantification, and Machine Learning

National Institute of Standards and Technology(美国国家标准与技术研究院);University of Massachusetts Chan Medical School(马萨诸塞大学陈医学院)

Paul N. Patrone, Raquel A. Binder, Catherine S. Forconi, Ann M. Moormann, Anthony J. Kearsley

AI总结:

本文研究诊断测试中分类理论与患病率的联系,通过引理证明患病率加权误差分类器与贝叶斯最优分类器等效,提出同伦算法估计水平集,并验证其不确定性量化效果。

摘要:

诊断测试为分类理论的研究和工具开发提供了独特的场景。在此类背景下,患病率(prevalence)的概念,即患有特定疾病的个体数量,是基础性的,它既是一个固有的关注量,也是控制分类准确率的参数。本手稿是分为两部分系列的第一部分,研究分类理论与患病率之间更深层的联系,展示后者如何为某些类型的机器学习(ML)建立更完整的不确定性量化(UQ)理论。我们通过一个引理来推动这一分析,该引理表明,最小化患病率加权误差的一般分类器包含与依赖条件概率密度的贝叶斯最优分类器相同的概率信息。这促使我们研究相对概率水平集 $B^\star (q)$,它被重新解释为分类边界和量化类标签不确定性的有用工具。为了在实践中实现这一点,我们还提出了一种数值同伦算法,通过最小化患病率加权经验误差来估计 $B^\star (q)$。该方法的成功与不足促使我们重新审视水平集的性质,我们推导出相应的分类器遵循一个有用的单调性属性,该属性稳定了数值计算并指向了机器学习不确定性量化(UQ)的重要扩展。在整个过程中,我们在合成数据和仅供研究使用的 SARS-CoV-2 酶联免疫吸附测定(ELISA)检测背景下验证了我们的方法。

英文摘要:

Diagnostic testing provides a unique setting for studying and developing tools in classification theory. In such contexts, the concept of prevalence, i.e. the number of individuals with a given condition, is fundamental, both as an inherent quantity of interest and as a parameter that controls classification accuracy. This manuscript is the first in a two-part series that studies deeper connections between classification theory and prevalence, showing how the latter establishes a more complete theory of uncertainty quantification (UQ) for certain types of machine learning (ML). We motivate this analysis via a lemma demonstrating that general classifiers minimizing a prevalence-weighted error contain the same probabilistic information as Bayes-optimal classifiers, which depend on conditional probability densities. This leads us to study relative probability level-sets $B^\star (q)$, which are reinterpreted as both classification boundaries and useful tools for quantifying uncertainty in class labels. To realize this in practice, we also propose a numerical, homotopy algorithm that estimates the $B^\star (q)$ by minimizing a prevalence-weighted empirical error. The successes and shortcomings of this method motivate us to revisit properties of the level sets, and we deduce the corresponding classifiers obey a useful monotonicity property that stabilizes the numerics and points to important extensions to UQ of ML. Throughout, we validate our methods in the context of synthetic data and a research-use-only SARS-CoV-2 enzyme-linked immunosorbent (ELISA) assay.

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。

↑