BriefGPT.xyz
Sep, 2024
揭示海森矩阵：平滑收敛损失函数景观的关键
Unraveling the Hessian: A Key to Smooth Convergence in Loss Function Landscapes
HTML
PDF
Nikita Kiselev, Andrey Grabovoy
TL;DR
本研究解决了神经网络损失景观在样本量增加时变化的未探索问题。通过理论分析和实证研究，展示了损失函数在图像分类任务上的收敛性，并为样本量确定技术的发展提供了重要启示。
Abstract
The
loss landscape
of
neural networks
is a critical aspect of their training, and understanding its properties is essential for improving their performance. In this paper, we investigate how the loss surface chan
→