Near-Optimal Policies for Dynamic Multinomial Logit Assortment Selection Models
Near-Optimal Policies for Dynamic Multinomial Logit Assortment Selection Models
复制标题
动态多项 Logit 分类选择模型的近最优策略
DOI：
--
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
Yuanshuo Zhou
中科院分区：
文献类型：
--
作者：
Yining Wang;Xi Chen;Yuanshuo Zhou
本文研究了无能力多项式-logit （MNL）模型下的动态分类选择问题。通过仔细分析收益潜力函数，我们表明基于三切分的算法实现了O（sqrt(T log log T)）的项目无关遗憾界，它与迭代对数项的信息理论下界相匹配。我们的证明技术从单峰/凸强盗文献中提取工具，以及极小极大多臂强盗问题中的自适应置信参数。
In this paper we consider the dynamic assortment selection problem under an uncapacitated multinomial-logit (MNL) model. By carefully analyzing a revenue potential function, we show that a trisection based algorithm achieves an item-independent regret bound of O(sqrt(T log log T), which matches information theoretical lower bounds up to iterated logarithmic terms. Our proof technique draws tools from the unimodal/convex bandit literature as well as adaptive confidence parameters in minimax multi-armed bandit problems.