Distribution-Free Rates in Neyman-Pearson Classification
Not on the map. Why?
Abstract (arXiv)
We consider the problem of Neyman-Pearson classification which models unbalanced classification settings where error w.r.t. a distribution μ1 is to be minimized subject to low error w.r.t. a different distribution μ0. Given a fixed VC class 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 (μ0, μ1). The rates involve a dichotomy between hard and easy classes H as characterized by a simple geometric condition, a three-points-separation condition, loosely related to VC dimension.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 10 of its 29 references that are in the map. First posted on arXiv 14 Feb 2024.
Builds on
10 of 29 references.
References · 10
- 2015The Optimal Sample Complexity of PAC Learningcited by 72
- 2019Quadratically Regularized Subgradient Methods for Weakly Convex Optimization with Weakly Convex Constraintscited by 25
- 2022Bayes-Optimal Classifiers under Group Fairnesscited by 24
- 2018A Generalized Neyman-Pearson Criterion for Optimal Domain Adaptationcited by 22
- 2016Neyman-Pearson (NP) classification algorithms and NP receiver operating characteristics (NP-ROC)cited by 18
- 2018Neyman-Pearson classification: parametrics and sample size requirementcited by 8
- 2019EDIMA: Early Detection of IoT Malware Network Activity Using Machine Learning Techniquescited by 8
- 2015Neyman-Pearson Classification under High-Dimensional Settingscited by 5
- 2023GBM-based Bregman Proximal Algorithms for Constrained Learningcited by 1
- 2023Neyman-Pearson and equal opportunity: when efficiency meets fairness in classificationcited by 1
Built on by
Citing papers per year: 2025: 2; 2026: 1.
3 papers.