arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.02330econ.EMstat.ML
收藏

自适应组合分配

Adaptive Combinatorial Allocation

Maximilian Kasy, Alexander Teytelboym

摘要:

我们考虑的设置,分配必须反复选择,回报是未知的,但可以学习,决策受到约束。我们的模型涵盖了双侧和单侧匹配,即使有复杂的约束。我们提出了一种基于汤普森采样的方法。我们的主要结果是一个先验独立的有限样本界的期望遗憾,这个算法。虽然分配的数量随着参与者的数量呈指数级增长,但界限并不取决于此数量。我们说明了我们的算法使用数据在美国的难民安置的性能。

英文摘要:

We consider settings where an allocation has to be chosen repeatedly, returns are unknown but can be learned, and decisions are subject to constraints. Our model covers two-sided and one-sided matching, even with complex constraints. We propose an approach based on Thompson sampling. Our main result is a prior-independent finite-sample bound on the expected regret for this algorithm. Although the number of allocations grows exponentially in the number of participants, the bound does not depend on this number. We illustrate the performance of our algorithm using data on refugee resettlement in the United States.

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。

↑