BriefGPT.xyz
Nov, 2018
非凸在线学习中的本地遗憾
A Local Regret in Nonconvex Online Learning
HTML
PDF
Sergul Aydore, Lee Dicker, Dean Foster
TL;DR
本文讨论了基于梯度的在线学习算法来预测非凸模型序列的结果,提出了一种比标准regret更可解释的新定义来评估预测问题的性能并给出了该定义的边界分析。
Abstract
We consider an
online learning
process to forecast a sequence of outcomes for
nonconvex models
. A typical measure to evaluate
online learning
→