We consider the problem of Neyman-Pearson classification which models unbalanced classification settings where error w.r.t. a distribution $μ_1$ is to be minimized subject to low error w.r.t. a different distribution $μ_0$. Given a fixed VC class $\mathcal{H}$ of classifiers to be minimized over, we provide a full characterization of possible distribution-free rates, i.e., minimax rates over the space of all pairs $(μ_0, μ_1)$. The rates involve a dichotomy between hard and easy classes $\mathcal{H}$ as characterized by a simple geometric condition, a three-points-separation condition, loosely related to VC dimension.
Intentional Control of Type I Error over Unconscious Data Distortion: a Neyman-Pearson Approach to Text Classification
Hong Kong University of Science and Technology（香港科技大学）；The Pennsylvania State University（宾夕法尼亚州立大学）；University of Hong Kong（香港大学）；University of Southern California（南加州大学）
Hierarchical Neyman-Pearson Classification for Prioritizing Severe Disease Categories in COVID-19 Patient Data
City University of Hong Kong（香港城市大学）；University of Sydney（悉尼大学）；University of California, Los Angeles（加利福尼亚大学洛杉矶分校）；University of Southern California（南加利福尼亚大学）
Know When to Abstain: Optimal Selective Classification with Likelihood Ratios
Department of Computer Science, National University of Singapore（计算机科学系，国立新加坡大学）；Smart Systems Institute, National University of Singapore（智能系统研究所，国立新加坡大学）
Indian Institute of Science（印度科学学院）；Univ. Grenoble Alpes（格勒诺布尔阿尔卑斯大学）；Inria（法国国家信息与自动化研究所）；CNRS（法国国家科学研究中心）；Grenoble INP（格勒诺布尔国立理工学院）；MPI-SWS（马克斯·普朗克软件系统研究所）
