arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2503.00565stat.MLcs.LGmath.STstat.MEstat.TH
收藏

批量单索引全局多臂老虎机与协变量

Batched Single-Index Global Multi-Armed Bandits with Covariates

Department of Mathematics, Applied Mathematics and Statistics, Case Western Reserve University(数学系、应用数学与统计学系,凯斯西储大学);Department of Statistics, Pennsylvania State University(统计系,宾夕法尼亚州立大学)

Sakshi Arya, Hyebin Song

AI总结:

本文提出了一种新的半参数框架,用于带有协变量的批量老虎机问题,通过引入共享参数和单索引回归模型来捕捉臂奖励之间的关系,提出BIDS算法,在两种设置下推导了理论遗憾界,证明了在协变量维度为1时非参数批量老虎机的最优率。

摘要:

多臂老虎机(MAB)框架是一种广泛用于顺序决策制定的方法,其中决策者在每一轮中选择一个臂,以最大化长期奖励。在许多实际应用中,如个性化医学和推荐系统,决策时可用上下文信息,不同臂的奖励相关而非独立,且反馈以批量形式提供。我们提出了一种新的半参数框架,用于带有协变量的批量老虎机,该框架在臂之间共享参数。我们利用单索引回归(SIR)模型来捕捉臂奖励之间的关系,同时在可解释性和灵活性之间取得平衡。我们的算法,批量单索引动态分箱和 successive arm elimination(BIDS),采用批量 successive arm elimination 策略,并通过单索引方向引导的动态分箱机制。我们考虑了两种设置:一种是可用 pilot 方向,另一种是方向从数据估计,推导了两种情况的理论遗憾界。当 pilot 方向足够准确且臂的数量 K 固定时,我们的方法在非参数批量老虎机中实现了最小化最优率(d=1),规避了维度灾难。在模拟和现实数据集上的大量实验展示了我们的算法相比由 \cite{jiang2025batched} 引入的非参数批量老虎机方法的有效性。

英文摘要:

The multi-armed bandits (MAB) framework is a widely used approach for sequential decision-making, where a decision-maker selects an arm in each round with the goal of maximizing long-term rewards. In many practical applications, such as personalized medicine and recommendation systems, contextual information is available at the time of decision-making, rewards from different arms are related rather than independent, and feedback is provided in batches. We propose a novel semi-parametric framework for batched bandits with covariates that incorporates a shared parameter across arms. We leverage the single-index regression (SIR) model to capture relationships between arm rewards while balancing interpretability and flexibility. Our algorithm, Batched single-Index Dynamic binning and Successive arm elimination (BIDS), employs a batched successive arm elimination strategy with a dynamic binning mechanism guided by the single-index direction. We consider two settings: one where a pilot direction is available and another where the direction is estimated from data, deriving theoretical regret bounds for both cases. When a pilot direction is available with sufficient accuracy and the number of arms $K$ is fixed, our approach achieves minimax-optimal rates (with $d = 1$) for nonparametric batched bandits, circumventing the curse of dimensionality. Extensive experiments on simulated and real-world datasets demonstrate the effectiveness of our algorithm compared to the nonparametric batched bandit method introduced by \cite{jiang2025batched}.

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。

↑