arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.11370cs.LGmath.OC
收藏

带连续切换约束的在线凸优化

Online Convex Optimization with Continuous Switching Constraint

National Key Laboratory for Novel Software Technology(计算机软件新技术国家重点实验室);Nanjing University(南京大学);the University of Iowa(爱荷华大学)

Guanghui Wang, Yuanyu Wan, Tianbao Yang, Lijun Zhang

摘要:

在许多顺序决策应用中,决策的改变会带来额外的成本,例如与改变服务器状态相关联的损耗成本。为了控制切换成本,我们引入了连续切换约束的在线凸优化问题,其目标是在给定\emph{overall}切换成本的预算的情况下实现小的遗憾。我们首先调查的困难的问题,并提供了一个下界的顺序$Ω(\sqrt{T})$时,切换成本预算$S=Ω(\sqrt{T})$,和$Ω(\min\{\frac{T}{S},T\})$时,$S=O(\sqrt{T})$,其中$T$是时间范围。其基本思想是精心设计一个自适应对手,谁可以调整的损失函数,根据累积的转换成本的球员到目前为止,基于正交技术。然后,我们开发了一个简单的基于梯度的算法,享有极大极小最优遗憾界。最后,我们证明了,对于强凸函数,遗憾界可以改进为$S=Ω(\log T)$的$O(\log T)$,和$O(\min\{T/\exp(S)+S,T\})$的$S=O(\log T)$。

英文摘要:

In many sequential decision making applications, the change of decision would bring an additional cost, such as the wear-and-tear cost associated with changing server status. To control the switching cost, we introduce the problem of online convex optimization with continuous switching constraint, where the goal is to achieve a small regret given a budget on the \emph{overall} switching cost. We first investigate the hardness of the problem, and provide a lower bound of order $Ω(\sqrt{T})$ when the switching cost budget $S=Ω(\sqrt{T})$, and $Ω(\min\{\frac{T}{S},T\})$ when $S=O(\sqrt{T})$, where $T$ is the time horizon. The essential idea is to carefully design an adaptive adversary, who can adjust the loss function according to the cumulative switching cost of the player incurred so far based on the orthogonal technique. We then develop a simple gradient-based algorithm which enjoys the minimax optimal regret bound. Finally, we show that, for strongly convex functions, the regret bound can be improved to $O(\log T)$ for $S=Ω(\log T)$, and $O(\min\{T/\exp(S)+S,T\})$ for $S=O(\log T)$.

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。

↑