BriefGPT.xyz
Dec, 2021
针对超出分布检测的可证明保障
Provable Guarantees for Understanding Out-of-distribution Detection
HTML
PDF
Peyman Morteza, Yixuan Li
TL;DR
本文研究了如何检测机器学习模型移植到实际应用中可能出现的数据分布偏移，提出了一个以神经网络为基础的OOD检测方法，并结合理论与实验表现对其进行了分析与评估。
Abstract
Out-of-distribution (OOD) detection is important for deploying
machine learning models
in the real world, where test data from shifted distributions can naturally arise. While a plethora of
algorithmic approaches
→