BriefGPT.xyz
Feb, 2018
神经网络二元分类的损失曲面理解
Understanding the Loss Surface of Neural Networks for Binary Classification
HTML
PDF
Shiyu Liang, Ruoyu Sun, Yixuan Li, R. Srikant
TL;DR
针对单层神经网络的拟合损失函数，研究神经网络算法中局部极小值的性质，提出当神经元是严格凸函数并且代理损失函数是铰链损失函数的平滑版本时，在所有局部极小值处训练误差为零的条件。同时，通过反例表明当损失函数替换为二次损失或逻辑损失时，该结论可能不成立。
Abstract
It is widely conjectured that the reason that training algorithms for
neural networks
are successful because all
local minima
lead to similar performance, for example, see (LeCun et al., 2015, Choromanska et al.,
→