BriefGPT.xyz
Apr, 2023
过拟合元学习的泛化性能理论特征化
Theoretical Characterization of the Generalization Performance of Overfitted Meta-Learning
HTML
PDF
Peizhong Ju, Yingbin Liang, Ness B. Shroff
TL;DR
本文研究了使用高斯特征的线性回归模型下过拟合元学习的泛化性能,发现过拟合的MAML最小L2规范解可以有效降低泛化误差。
Abstract
meta-learning
has arisen as a successful method for improving training performance by training over many similar tasks, especially with deep neural networks (DNNs). However, the theoretical understanding of when and why
→