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 1810.03024cs.LGstat.ML
收藏

非平稳下的学习优化

Learning to Optimize under Non-Stationarity

ISEM, NUS(新加坡国立大学工业与系统工程系);IDSS, MIT(麻省理工学院信息与决策系统实验室);SDSC, MIT(麻省理工学院斯隆数据科学中心)

Wang Chi Cheung, David Simchi-Levi, Ruihao Zhu

摘要:

我们介绍的算法,实现国家的最先进的\emph{dynamic regret}界的非平稳线性随机强盗设置。它捕捉自然的应用程序,如动态定价和广告分配在不断变化的环境。我们展示了如何克服由非平稳性所带来的困难,可以通过一个新的婚姻之间的随机和敌对的土匪学习算法。定义$d,B_T,$和$T$为问题的维度,\emph{variation budget},和总的时间范围,分别,我们的主要贡献是调整滑动窗口UCB(\texttt{SW-UCB})算法与最佳的$\widetilde{O}(d^{2/3}(B_T+1)^{1/3}T^{2/3})$动态遗憾,和调整自由bandit-over-bandit(\texttt{BOB})框架建立在\texttt{SW-UCB}算法与最佳的$\widetilde{O}(d^{2/3}(B_T+1)^{1/4}T^{3/4})$动态遗憾。

英文摘要:

We introduce algorithms that achieve state-of-the-art \emph{dynamic regret} bounds for non-stationary linear stochastic bandit setting. It captures natural applications such as dynamic pricing and ads allocation in a changing environment. We show how the difficulty posed by the non-stationarity can be overcome by a novel marriage between stochastic and adversarial bandits learning algorithms. Defining $d,B_T,$ and $T$ as the problem dimension, the \emph{variation budget}, and the total time horizon, respectively, our main contributions are the tuned Sliding Window UCB (\texttt{SW-UCB}) algorithm with optimal $\widetilde{O}(d^{2/3}(B_T+1)^{1/3}T^{2/3})$ dynamic regret, and the tuning free bandit-over-bandit (\texttt{BOB}) framework built on top of the \texttt{SW-UCB} algorithm with best $\widetilde{O}(d^{2/3}(B_T+1)^{1/4}T^{3/4})$ dynamic regret.

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。

↑