arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1811.05095cs.LGstat.ML
收藏

非凸在线学习中的局部后悔

A Local Regret in Nonconvex Online Learning

Stevens Institute of Technology(史蒂文斯理工学院);Amazon(亚马逊)

Sergul Aydore, Lee Dicker, Dean Foster

摘要:

我们考虑一个在线学习过程来预测非凸模型的结果序列。评价在线学习算法的一个典型的度量是后悔,但是这种后悔的标准定义对于非凸模型是难以处理的,即使在离线设置中。因此,基于梯度的遗憾定义是常见的离线和在线非凸问题。最近,引入了基于局部梯度的后悔的概念。受校准和基于局部梯度的遗憾的概念的启发,我们引入了另一种遗憾的定义,我们讨论了为什么我们的定义是更可解释的预测问题。在一定的假设条件下,我们还对我们的遗憾进行了约束分析。

英文摘要:

We consider an online learning process to forecast a sequence of outcomes for nonconvex models. A typical measure to evaluate online learning algorithms is regret but such standard definition of regret is intractable for nonconvex models even in offline settings. Hence, gradient based definition of regrets are common for both offline and online nonconvex problems. Recently, a notion of local gradient based regret was introduced. Inspired by the concept of calibration and a local gradient based regret, we introduce another definition of regret and we discuss why our definition is more interpretable for forecasting problems. We also provide bound analysis for our regret under certain assumptions.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑