BriefGPT.xyz
Nov, 2020
当优化$f$-散度对标签噪声具有鲁棒性时
When Optimizing $f$-divergence is Robust with Label Noise
HTML
PDF
Jiaheng Wei, Yang Liu
TL;DR
本文利用$f$-divergence的变分形式证明了其在标签噪声存在时具有良好的鲁棒性,并将其应用于噪声标签下的学习问题中,并提出了可能不具鲁棒性的解决方法,并通过实证研究证明了该方法的有效性。
Abstract
We show when maximizing a properly defined $f$-divergence measure with respect to a classifier's predictions and the supervised labels is robust with
label noise
. Leveraging its
variational form
, we derive a nice
→