arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.07049quant-phcs.DScs.LG
收藏

多臂强盗的量子探测算法

Quantum exploration algorithms for multi-armed bandits

Joint Center for Quantum Information and Computer Science, University of Maryland(马里兰大学量子信息与计算机科学联合中心);Department of Mathematics, University of Maryland(马里兰大学数学系);Department of Computer Science and Institute for Advanced Computer Studies, University of Maryland(马里兰大学计算机科学系与高级计算机研究所);Center for Theoretical Physics, Massachusetts Institute of Technology(麻省理工学院理论物理中心)

Daochen Wang, Xuchen You, Tongyang Li, Andrew M. Childs

摘要:

确定多臂强盗的最佳手臂是强盗优化的核心问题。我们研究了这个问题的量子计算版本与相干的预言机访问状态编码的奖励概率的每个手臂作为量子振幅。具体来说,我们可以找到最好的手臂与固定的信心,使用$\tilde{O}\bigl(\sqrt{\sum_{i=2}^nΔ^{\smash{-2}}_i}\bigr)$量子查询,其中$Δ_{i}$表示最好的手臂和$i^\text{th}$ -最好的arm. This算法的平均奖励之间的差异,基于可变时间的幅度放大和估计,给出了二次加速比最好的经典结果。我们还证明了一个匹配的量子下界(多对数因子)。

英文摘要:

Identifying the best arm of a multi-armed bandit is a central problem in bandit optimization. We study a quantum computational version of this problem with coherent oracle access to states encoding the reward probabilities of each arm as quantum amplitudes. Specifically, we show that we can find the best arm with fixed confidence using $\tilde{O}\bigl(\sqrt{\sum_{i=2}^nΔ^{\smash{-2}}_i}\bigr)$ quantum queries, where $Δ_{i}$ represents the difference between the mean reward of the best arm and the $i^\text{th}$-best arm. This algorithm, based on variable-time amplitude amplification and estimation, gives a quadratic speedup compared to the best possible classical result. We also prove a matching quantum lower bound (up to poly-logarithmic factors).

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。

↑