arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2512.06758cs.LG
收藏

匹配市场中带bandit学习的最优分析:串行独裁假设

Optimal Analysis for Bandit Learning in Matching Markets with Serial Dictatorship

Shanghai Jiao Tong University(上海交通大学)

Zilong Wang, Shuai Li

AI总结:

本文提出了一种多级连续选择算法,在串行独裁假设下实现了匹配市场带bandit学习问题的最优后悔界。

摘要:

两面匹配市场的问题在计算机科学和经济学中已被广泛研究,因其在众多领域中的广泛应用。由于市场参与者在各种在线匹配平台上通常不确定他们的偏好,一个新兴的研究方向致力于在线设置,其中一方参与者(玩家)通过与另一方(臂)的多轮互动来学习其未知的偏好。Sankararaman等人在串行独裁假设下为该问题提供了Ω(N log T/Δ² + K log T/Δ)的后悔下界,其中N是玩家的数量,K(≥N)是臂的数量,Δ是玩家和臂之间最小的奖励差距,T是时间范围。串行独裁假设认为臂有相同的偏好,这在现实情况下当一方参与者有统一的评估标准时是常见的。最近,Kong和Li提出了ET-GS算法,并实现了O(K log T/Δ²)的后悔上界,这是目前最好的上界。然而,下界和上界之间仍存在从N到K的差距。不清楚是下界还是上界需要改进。在本文中,我们提出了一种多级连续选择算法,当市场满足串行独裁时,获得了O(N log T/Δ² + K log T/Δ)的后悔界。据我们所知,我们是第一个提出在带bandit的匹配市场问题中匹配下界的算法。

英文摘要:

The problem of two-sided matching markets is well-studied in computer science and economics, owing to its diverse applications across numerous domains. Since market participants are usually uncertain about their preferences in various online matching platforms, an emerging line of research is dedicated to the online setting where one-side participants (players) learn their unknown preferences through multiple rounds of interactions with the other side (arms). Sankararaman et al. provide an $Ω\left( \frac{N\log(T)}{Δ^2} + \frac{K\log(T)}Δ \right)$ regret lower bound for this problem under serial dictatorship assumption, where $N$ is the number of players, $K (\geq N)$ is the number of arms, $Δ$ is the minimum reward gap across players and arms, and $T$ is the time horizon. Serial dictatorship assumes arms have the same preferences, which is common in reality when one side participants have a unified evaluation standard. Recently, the work of Kong and Li proposes the ET-GS algorithm and achieves an $O\left( \frac{K\log(T)}{Δ^2} \right)$ regret upper bound, which is the best upper bound attained so far. Nonetheless, a gap between the lower and upper bounds, ranging from $N$ to $K$, persists. It remains unclear whether the lower bound or the upper bound needs to be improved. In this paper, we propose a multi-level successive selection algorithm that obtains an $O\left( \frac{N\log(T)}{Δ^2} + \frac{K\log(T)}Δ \right)$ regret bound when the market satisfies serial dictatorship. To the best of our knowledge, we are the first to propose an algorithm that matches the lower bound in the problem of matching markets with bandits.

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。

↑