BriefGPT.xyz
Apr, 2023
迁移学习下的模型选择限制
Limits of Model Selection under Transfer Learning
HTML
PDF
Steve Hanneke, Samory Kpotufe, Yasaman Mahdaviyeh
TL;DR
研究表明，在模型选择中，转移距离是一个新的复杂度项，但在分类中，自适应速率可能会非常缓慢，而需有关距离的知识的oracle速率则可以达到更快的速度。
Abstract
Theoretical studies on
transfer learning
or
domain adaptation
have so far focused on situations with a known hypothesis class or model; however in practice, some amount of
→