BriefGPT.xyz
Nov, 2023
关于强健的过拟合：对抗训练引起的分布问题
On robust overfitting: adversarial training induced distribution matters
HTML
PDF
Runzhi Tian, Yongyi Mao
TL;DR
该研究论文探讨了对抗训练中的鲁棒性过拟合现象及其与扰动诱导分布的泛化困难性之间的相关性，提供了一个新的上界，其中称为“局部离散性”的扰动算子发挥了重要作用。
Abstract
adversarial training
may be regarded as standard training with a modified loss function. But its
generalization error
appears much larger than standard training under standard loss. This phenomenon, known as
→