paper-with-me

Papers

On the Learnability of Out-of-distribution Detection

2024-04-07 · Zhen Fang, Yixuan Li, Feng Liu, Bo Han, Jie Lu

Supervised learning aims to train a classifier under the assumption that training and test data are from the same distribution. To ease the above assumption, researchers have studied a more realistic setting: out-of-distribution (OOD) detection, where test data may come from classes that are unknown during training (i.e., OOD data). Due to the unavailability and diversity of OOD data, good generalization ability is crucial for effective OOD detection algorithms, and corresponding learning theory is still an open problem. To study the generalization of OOD detection, this paper investigates the probably approximately correct (PAC) learning theory of OOD detection that fits the commonly used evaluation metrics in the literature. First, we find a necessary condition for the learnability of OOD detection. Then, using this condition, we prove several impossibility theorems for the learnability of OOD detection under some scenarios. Although the impossibility theorems are frustrating, we find that some conditions of these impossibility theorems may not hold in some practical scenarios. Based on this observation, we next give several necessary and sufficient conditions to characterize the learnability of OOD detection in some practical scenarios. Lastly, we offer theoretical support for representative OOD detection works based on our OOD theory.

📄 PDF Abstract BibTeX arXiv:2404.04865

Code (0)

등록된 구현이 없습니다.

Tasks

Learning TheoryOut-of-Distribution DetectionOut of Distribution (OOD) DetectionPAC learning

Similar Papers 제목 키워드 기반

A Closer Look at the Learnability of Out-of-Distribution (OOD) Detection

2025-01-15 · Konstantin Garov, Kamalika Chaudhuri

Machine learning algorithms often encounter different or "out-of-distribution" (OOD) data at deployment time, and OOD detection is frequently employed to detect these examples. While it works reasonably well in practice,…

Learning TheoryOut of Distribution (OOD) DetectionPAC learning

Is Out-of-Distribution Detection Learnable?

2022-10-26 · Zhen Fang, Yixuan Li, Jie Lu, Jiahua Dong 외

Supervised learning aims to train a classifier under the assumption that training and test data are from the same distribution. To ease the above assumption, researchers have studied a more realistic setting: out-of-dist…

DiversityLearning TheoryOut-of-Distribution DetectionOut of Distribution (OOD) Detection+1

Distribution Learnability and Robustness

2024-06-25 · NeurIPS 2023 11 · Shai Ben-David, Alex Bie, Gautam Kamath, Tosca Lechner

We examine the relationship between learnability and robust (or agnostic) learnability for the problem of distribution learning. We show that, contrary to other learning settings (e.g., PAC learning of function classes),…

PAC learning

How Out-of-Distribution Detection Learning Theory Enhances Transformer: Learnability and Reliability

2024-06-13 · Yijin Zhou, Yutang Ge, Xiaowen Dong, Yuguang Wang

Transformers excel in natural language processing and computer vision tasks. However, they still face challenges in generalizing to Out-of-Distribution (OOD) datasets, i.e. data whose distribution differs from that seen …

Image ClassificationLearning TheoryOut-of-Distribution Detection

On the Learnability of Distribution Classes with Adaptive Adversaries

2025-09-05 · Tosca Lechner, Alex Bie, Gautam Kamath arxiv

We consider the question of learnability of distribution classes in the presence of adaptive adversaries -- that is, adversaries capable of intercepting the samples requested by a learner and applying manipulations with …