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 2210.04774math.OCecon.TH
收藏

在线资源分配示例

Online Resource Allocation with Samples

Negin Gorlezaei, Patrick Jaillet, Zijie Zhou

摘要:

我们研究了在线资源分配问题的不确定性下的需求和奖励的每种类型的需求(代理)的资源。尽管处理资源分配问题中的需求不确定性一直是文献中许多论文的主题,但不知道回报的挑战几乎没有探讨过。缺乏关于代理奖励的知识是由分配新资源的单元的问题引起的(例如,新开发的疫苗或药物),效力/价值未知。对于这样的设置,我们假设我们可以在分配期开始之前\emph{test}市场。在测试期间,我们以概率$p$对市场中的每个代理进行抽样。我们研究如何最佳地利用\emph{sample information}在我们的在线资源分配问题下的对抗到达过程。我们提出了一个渐近最优算法,实现$1-Θ(1/(p\sqrt{m}))$竞争比,其中$m$是可用的资源单元的数量。通过刻画任何随机和确定性算法的竞争比的上界,我们证明了我们的$1-Θ(1/(p\sqrt{m}))$的竞争比对任何$p =ω(1/\sqrt{m})$都是紧的.样本信息的渐近最优性是可能的,这突出了为新资源运行测试期的显著优势。我们使用包含不同年龄组COVID-19相关住院患者数量的数据集证明了我们提出的算法的有效性。

英文摘要:

We study an online resource allocation problem under uncertainty about demand and about the reward of each type of demand (agents) for the resource. Even though dealing with demand uncertainty in resource allocation problems has been the topic of many papers in the literature, the challenge of not knowing rewards has been barely explored. The lack of knowledge about agents' rewards is inspired by the problem of allocating units of a new resource (e.g., newly developed vaccines or drugs) with unknown effectiveness/value. For such settings, we assume that we can \emph{test} the market before the allocation period starts. During the test period, we sample each agent in the market with probability $p$. We study how to optimally exploit the \emph{sample information} in our online resource allocation problem under adversarial arrival processes. We present an asymptotically optimal algorithm that achieves $1-Θ(1/(p\sqrt{m}))$ competitive ratio, where $m$ is the number of available units of the resource. By characterizing an upper bound on the competitive ratio of any randomized and deterministic algorithm, we show that our competitive ratio of $1-Θ(1/(p\sqrt{m}))$ is tight for any $p =ω(1/\sqrt{m})$. That asymptotic optimality is possible with sample information highlights the significant advantage of running a test period for new resources. We demonstrate the efficacy of our proposed algorithm using a dataset that contains the number of COVID-19 related hospitalized patients across different age groups.

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。

↑