BriefGPT.xyz
Jan, 2022
学习域不变表示特征的条件熵最小化原则
Conditional entropy minimization principle for learning domain invariant representation features
HTML
PDF
Thuan Nguyen, Boyang Lyu, Prakash Ishwar, Matthias Scheutz, Shuchin Aeron
TL;DR
提出了一种基于条件熵最小化原则的框架，用于过滤混入小说不变特征的不变特征，以增强新算法的泛化能力。
Abstract
Invariance principle-based methods, for example,
invariant risk minimization
(IRM), have recently emerged as promising approaches for
domain generalization
(DG). Despite the promising theory, invariance principle
→