Asymmetric Error Control Under Imperfect Supervision: A Label-Noise-Adjusted Neyman–Pearson Umbrella Algorithm

DOI10.1080/01621459.2021.2016423MaRDI QIDQ6077576zbMATH OpenOpenAlexFDO

Authors Xin Tong, Gareth M. James

Publication date 18 October 2023

Published in Journal of the American Statistical Association (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2112.00314

zbMATH Keywords

classificationlabel noiseNeyman-Pearson (NP) paradigmtype I errorumbrella algorithm

Mathematics Subject Classification ID

Statistics (62-XX)

Abstract: Label noise in data has long been an important problem in supervised learning applications as it affects the effectiveness of many widely used classification methods. Recently, important real-world applications, such as medical diagnosis and cybersecurity, have generated renewed interest in the Neyman-Pearson (NP) classification paradigm, which constrains the more severe type of error (e.g., the type I error) under a preferred level while minimizing the other (e.g., the type II error). However, there has been little research on the NP paradigm under label noise. It is somewhat surprising that even when common NP classifiers ignore the label noise in the training stage, they are still able to control the type I error with high probability. However, the price they pay is excessive conservativeness of the type I error and hence a significant drop in power (i.e., $1-$ type II error). Assuming that domain experts provide lower bounds on the corruption severity, we propose the first theory-backed algorithm that adapts most state-of-the-art classification methods to the training label noise under the NP paradigm. The resulting classifiers not only control the type I error with high probability under the desired level but also improve power.

Cites work

• A Neyman–Pearson Approach to Statistical Learning
• A noise-detection based AdaBoost algorithm for mislabeled data
• A plug-in approach to Neyman-Pearson classification
• Classification with asymmetric label noise: consistency and maximal denoising
• Classification with imperfect training labels
• scientific article; zbMATH DE number 1333815 (Why is no real title available?)
• Neyman-Pearson classification under high-dimensional settings
• Neyman-Pearson classification, convexity and stochastic constraints
• Neyman-Pearson classification: parametrics and sample size requirement
• Noise modelling and evaluating learning from examples
• Noise tolerant variants of the perceptron algorithm
• Note on Initial Misclassification Effects on the Quadratic Discriminant Function

Cited in

(3)

• Classification with asymmetric label noise: consistency and maximal denoising
• Hierarchical Neyman-Pearson Classification for Prioritizing Severe Disease Categories in COVID-19 Patient Data
• Nonparametric receiver operating characteristic curve analysis with an imperfect gold standard

This page was built for publication: Asymmetric Error Control Under Imperfect Supervision: A Label-Noise-Adjusted Neyman–Pearson Umbrella Algorithm

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6077576)