# Neyman-Pearson Classification under Both Null and Alternative Distributions Shift

arXiv: https://arxiv.org/abs/2511.06641 · HTML: https://mlsanity.com/paper/2511.06641/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 31 references that are in the map.
- First posted on arXiv 10 Nov 2025.

## Builds on (most cited first, 11 of 11)

- [Convex optimization](https://mlsanity.com/paper/2106.01946/) (2021)
- [Size-Independent Sample Complexity of Neural Networks](https://mlsanity.com/paper/1712.06541/) (2017)
- [On the Theory of Transfer Learning: The Importance of Task Diversity](https://mlsanity.com/paper/2006.11650/) (2020)
- [Transfer Learning for High-dimensional Linear Regression: Prediction, Estimation, and Minimax Optimality](https://mlsanity.com/paper/2006.10593/) (2020)
- [Marginal Singularity, and the Benefits of Labels in Covariate-Shift](https://mlsanity.com/paper/1803.01833/) (2018)
- [On the Value of Target Data in Transfer Learning](https://mlsanity.com/paper/2002.04747/) (2020)
- [Minimax Lower Bounds for Transfer Learning with Linear and One-hidden Layer Neural Networks](https://mlsanity.com/paper/2006.10581/) (2020)
- [EDIMA: Early Detection of IoT Malware Network Activity Using Machine Learning Techniques](https://mlsanity.com/paper/1906.09715/) (2019)
- [Transfer Neyman-Pearson Algorithm for Outlier Detection](https://mlsanity.com/paper/2501.01525/) (2025)
- [Tight Rates in Supervised Outlier Transfer Learning](https://mlsanity.com/paper/2310.04686/) (2023)
- [Distribution-Free Rates in Neyman-Pearson Classification](https://mlsanity.com/paper/2402.09560/) (2024)

## Built on by (most cited first, 2 of 2)

- [An Efficient Variant of One-Class SVM with Lifelong Online Learning Guarantees](https://mlsanity.com/paper/2512.11052/) (2025)
- [Classification with Abstention Under Class-Conditional Error Constraints](https://mlsanity.com/paper/2609.22632/) (2026)

## Abstract (arXiv)

We consider the problem of transfer learning in Neyman-Pearson classification, where the objective is to minimize the error w.r.t. a distribution μ1, subject to the constraint that the error w.r.t. a distribution μ0 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 μ1, whereas in many practical scenarios shifts may occur in both μ0 and μ1. 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.