BriefGPT.xyz
Jun, 2020
Triple descent和两种过拟合:何时何处出现?
Triple descent and the two kinds of overfitting: Where & why do they appear?
HTML
PDF
Stéphane d'Ascoli, Levent Sagun, Giulio Biroli
TL;DR
本文研究深度学习中的双下降现象,即当训练样本数N接近模型参数数P或者输入维度D时,神经网络的泛化误差会出现峰值,本文提供了理论解释,并探讨了非线性对此现象的影响及正则化方法的应用。
Abstract
A recent line of research has highlighted the existence of a
double descent
phenomenon in deep learning, whereby increasing the number of training examples $N$ causes the generalization error of
neural networks
t
→