arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2305.01518stat.MEcs.AIcs.LGmath.STstat.OTstat.TH
收藏

定义预测规则的可复现性

Defining Replicability of Prediction Rules

Dana Farber Cancer Institute(丹娜-法伯癌症研究所);Harvard T.H. Chan School of Public Health(哈佛大学陈曾熙公共卫生学院)

Giovanni Parmigiani

AI总结:

受NAS报告启发,本文提出基于多智能体框架的预测规则可复现性定义方法,明确典型场景下“一致结果”的含义,将主流方法归为特例,为机器学习可复现性评估提供系统指导。

摘要:

本文提出了一种定义预测规则可复现性的方法。受美国国家科学院(NAS)近期一份报告的启发,本文从以下视角展开:可复现性是指在适于解决同一预测问题的多项研究中获得一致结果,且每项研究均获取了自身的数据。随后本文讨论了定义这一表述核心要素时涉及的概念与问题,重点聚焦典型应用场景中“一致结果”的含义,并提出一个用于定义可复现性的多智能体框架,框架中的智能体既非合作伙伴也非对手。本文将部分主流实用方法归为该框架的特例,以期为机器学习领域更系统的可复现性评估提供指导。

英文摘要:

In this article I propose an approach for defining replicability for prediction rules. Motivated by a recent NAS report, I start from the perspective that replicability is obtaining consistent results across studies suitable to address the same prediction question, each of which has obtained its own data. I then discuss concept and issues in defining key elements of this statement. I focus specifically on the meaning of "consistent results" in typical utilization contexts, and propose a multi-agent framework for defining replicability, in which agents are neither partners nor adversaries. I recover some of the prevalent practical approaches as special cases. I hope to provide guidance for a more systematic assessment of replicability in machine learning.

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。

↑