arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1406.7447cs.LG
收藏

单峰无平滑的强盗

Unimodal Bandits without Smoothness

Supelec(高等电力学院);KTH(瑞典皇家理工学院)

Richard Combes, Alexandre Proutiere

摘要:

考虑具有连续手臂的随机强盗问题,其中期望报酬是手臂的连续单峰函数,对期望报酬函数的光滑性和结构没有进一步的假设.针对这些问题,我们提出了随机五分法(SP)算法,并给出了有限时间后悔和优化误差的上界。特别是,我们表明,对于任何预期的奖励功能$μ$的行为作为$μ(x)=μ(x^\star)-C|x-x^\star|^ξ$本地周围的最大化$x^\star$的一些$ξ, C>0$,SP算法是顺序最优的。即当时间范围$T$变大时,其遗憾和优化误差尺度分别为$O(\sqrt{T\log(T)})$和$O(\sqrt{\log(T)/T})$。这些缩放是在不了解$ξ$和$C$的情况下实现的。我们的算法是基于渐近最优序贯统计检验,用于连续修剪的间隔,包含最好的手臂具有高概率。据我们所知,SP算法构成了第一个顺序臂选择规则,该规则分别实现了遗憾和优化误差缩放为$O(\sqrt{T})$和$O(1/\sqrt{T})$,对于非平滑的预期奖励函数以及具有未知平滑度的平滑函数,最高可达对数因子。

英文摘要:

We consider stochastic bandit problems with a continuous set of arms and where the expected reward is a continuous and unimodal function of the arm. No further assumption is made regarding the smoothness and the structure of the expected reward function. For these problems, we propose the Stochastic Pentachotomy (SP) algorithm, and derive finite-time upper bounds on its regret and optimization error. In particular, we show that, for any expected reward function $μ$ that behaves as $μ(x)=μ(x^\star)-C|x-x^\star|^ξ$ locally around its maximizer $x^\star$ for some $ξ, C>0$, the SP algorithm is order-optimal. Namely its regret and optimization error scale as $O(\sqrt{T\log(T)})$ and $O(\sqrt{\log(T)/T})$, respectively, when the time horizon $T$ grows large. These scalings are achieved without the knowledge of $ξ$ and $C$. Our algorithm is based on asymptotically optimal sequential statistical tests used to successively trim an interval that contains the best arm with high probability. To our knowledge, the SP algorithm constitutes the first sequential arm selection rule that achieves a regret and optimization error scaling as $O(\sqrt{T})$ and $O(1/\sqrt{T})$, respectively, up to a logarithmic factor for non-smooth expected reward functions, as well as for smooth functions with unknown smoothness.

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。

↑