arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.03158stat.MLcs.LG
收藏

缺失数据预测的简单插补规则:理论保证与实证表现的对比

Simple Imputation Rules for Prediction with Missing Data: Contrasting Theoretical Guarantees with Empirical Performance

London Business School(伦敦商学院)

Dimitris Bertsimas, Arthur Delarue, Jean Pauphilet

AI总结:

本文研究先插补后回归流程,证明一大类简单插补方法的渐近一致性,指出均值插补渐近最优而众数插补次优,并通过多类数据集验证理论与实践差距。

摘要:

缺失数据是现实世界数据集中的常见问题。本文通过对比理论证据与实证证据,研究“先插补后回归”流程的表现。我们针对一大类插补方法,建立了此类流程的渐近一致性。尽管常识认为“好”的插补方法会生成看似合理的数据集,但我们相反地表明,就预测而言,粗糙也可以是好的。除其他发现外,我们发现众数插补在渐近意义上次优,而均值插补在渐近意义上最优。随后,我们在由合成、半真实和真实数据集构成的大型语料上,详尽评估了这些理论结论的有效性。虽然我们收集的实证证据大体支持理论发现,但它也凸显了理论与实践之间的差距,以及未来研究的机会,涉及MAR假设的相关性、插补任务与回归任务之间复杂的相互依赖关系,以及对现实的合成数据生成模型的需求。

英文摘要:

Missing data is a common issue in real-world datasets. This paper studies the performance of impute-then-regress pipelines by contrasting theoretical and empirical evidence. We establish the asymptotic consistency of such pipelines for a broad family of imputation methods. While common sense suggests that a `good' imputation method produces datasets that are plausible, we show, on the contrary, that, as far as prediction is concerned, crude can be good. Among others, we find that mode-impute is asymptotically sub-optimal, while mean-impute is asymptotically optimal. We then exhaustively assess the validity of these theoretical conclusions on a large corpus of synthetic, semi-real, and real datasets. While the empirical evidence we collect mostly supports our theoretical findings, it also highlights gaps between theory and practice and opportunities for future research, regarding the relevance of the MAR assumption, the complex interdependency between the imputation and regression tasks, and the need for realistic synthetic data generation models.

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。

↑