arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.07005cs.LGstat.ML
收藏

组合分配赌博机与非线性臂效用

Combinatorial Allocation Bandits with Nonlinear Arm Utility

The University of Tokyo and RIKEN(东京大学和RIKEN);Keio University(庆应大学);Hanuku-kaso, Co., Ltd.(Hanuku-kaso公司)

Yuki Shibukawa, Koichi Tanaka, Yuta Saito, Shinji Ito

AI总结:

提出组合分配赌博机问题,通过臂满意度最大化而非正反馈数量,设计基于置信上界和汤普森采样的算法,实现近似遗憾界。

摘要:

匹配平台是一种匹配不同类型参与者(如公司和求职者)的系统。在这样的平台中,最大化匹配可能会将分配集中在受欢迎的参与者上,增加其他人的不满,最终导致流失,从而减少平台的盈利机会。为了解决这个问题,我们提出了一个新的在线学习问题,组合分配赌博机(CAB),它引入了*臂满意度*的概念。在CAB中,每一轮,学习器观察$K$个臂和$N$个用户的特征向量,将用户分配给臂,并观察遵循广义线性模型(GLM)的反馈。与先前工作不同,目标是最大化臂满意度而非正反馈的数量。对于CAB,我们开发了一种使用近似优化预言机的上置信界算法,并实现了近似遗憾上界,其对$d$、$T$和$N$的依赖与上下文组合线性赌博机的已知下界匹配(对数因子除外)。我们还分析了一种在精确优化预言机下具有标准遗憾界的汤普森采样算法,并提出了一种更便宜的单遍变体,在自洽性假设下保持次线性近似遗憾。在合成数据上的实验支持该目标,并表明CAB-UCB比基线实现了更高的累积满意度。

英文摘要:

A matching platform is a system that matches participants of different types, such as companies and job-seekers. In such a platform, maximizing matches may concentrate assignments on popular participants, increasing dissatisfaction among others, and eventually causing churn, which reduces the platform's profit opportunities. To address this issue, we propose a novel online learning problem, Combinatorial Allocation Bandits (CAB), which incorporates the notion of *arm satisfaction*. In CAB, at each round, the learner observes feature vectors for $K$ arms and $N$ users, assigns users to arms, and observes feedback following a generalized linear model (GLM). Unlike prior work, the objective is to maximize arm satisfaction rather than the number of positive feedback. For CAB, we develop an upper confidence bound algorithm that uses an approximate optimization oracle and achieves an approximate regret upper bound, whose dependence on $d$, $T$, and $N$ matches the known lower bound for contextual combinatorial linear bandits up to logarithmic factors. We also analyze a Thompson sampling algorithm with a standard regret bound under an exact optimization oracle, and propose a cheaper one-pass variant retaining sublinear approximate regret under a self-concordance assumption. Experiments on synthetic data support the objective and show that CAB-UCB achieves higher cumulative satisfaction than baselines.

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。

↑