Neyman-Pearson Classification under Both Null and Alternative Distributions Shift
Seyed Mohammadreza Mousavi Kalan, Yuyang Deng, Eitan J. Neugut, Samory Kpotufe
Abstract
We consider the problem of transfer learning in Neyman–Pearson classification, where the objective is to minimize the error w.r.t. a distribution , subject to the constraint that the error w.r.t. a distribution remains below a prescribed threshold. While transfer learning has been extensively studied in traditional classification, transfer learning in imbalanced classification such as Neyman–Pearson classification has received much less attention. This setting poses unique challenges, as both types of errors must be simultaneously controlled. Existing works address only the case of distribution shift in , whereas in many practical scenarios shifts may occur in both and . We derive an adaptive procedure that not only guarantees improved Type-I and Type-II errors when the source is informative, but also automatically adapt to situations where the source is uninformative, thereby avoiding negative transfer. In addition to such statistical guarantees, the procedures is efficient, as shown via complementary computational guarantees.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
Builds on3
- On the Theory of Transfer Learning: The Importance of Task DiversityNilesh Tripuraneni, Michael I. Jordan, Chi JinNeurIPS 2020 · 263 citations
- Minimax Lower Bounds for Transfer Learning with Linear and One-hidden Layer Neural NetworksSeyed Mohammadreza Mousavi Kalan, Zalan Fabian, Salman Avestimehr, Mahdi SoltanolkotabiNeurIPS 2020 · 37 citations
- Tight Rates in Supervised Outlier Transfer LearningMohammadreza M. Kalan, Samory KpotufeICLR 2024 · 4 citations
Related papers
- Balancing Positive and Negative Classification Error Rates in Positive-Unlabeled LearningXiming Li, Yuanchao Dai, Bing Wang, Changchun Li et al.NeurIPS 2025 · 3 citations
- Minimax and Neyman-Pearson Meta-Learning for Outlier LanguagesEdoardo Maria Ponti, Rahul Aralikatte, Disha Shrivastava, Siva Reddy et al.ACL Findings 2021
- Know When to Abstain: Optimal Selective Classification with Likelihood RatiosAlvin Heng, Harold SohICLR 2026 · 7 citations
- Positive-unlabeled AUC Maximization under Covariate ShiftAtsutoshi Kumagai, Tomoharu Iwata, Hiroshi Takahashi, Taishi Nishiyama et al.ICML 2025
- Learning from Positive and Unlabeled Data with Arbitrary Positive ShiftZayd Hammoudeh, Daniel LowdNeurIPS 2020 · 53 citations
