三篇新的研究论文探讨了老虎机算法的进展。一篇论文分析了线性高斯老虎机中 Thompson 采样算法的遗憾，表明了与先验相关的遗憾项和最小最大遗憾项可以解耦。另一篇论文提出了一种统一的误设减少方法，用于处理具有特定轮次可行决策集的非平稳线性老虎机，实现了最优的动态遗憾依赖。第三篇论文解决了具有重尾奖励的批量多臂老虎机问题，揭示了在某些情况下，更重的尾部实际上可能需要更少的批量即可获得接近最优的遗憾。
AI
arXiv:2607.07304v1 Announce Type: new Abstract: In this paper we first study the problem of generalized linear bandit (GLB) under heavy-tailed noise. The characteristics of heavy-tailed distributions are widely observed in real-world applications such as personalized recommendati…
In this paper we first study the problem of generalized linear bandit (GLB) under heavy-tailed noise. The characteristics of heavy-tailed distributions are widely observed in real-world applications such as personalized recommendation, financial markets, and medical treatments. B…
arXiv cs.LG
TIER_1English(EN)·Yifan Zhu, John C. Duchi, Benjamin Van Roy·
arXiv:2601.02022v2 Announce Type: replace Abstract: We prove that Thompson sampling exhibits $\tilde{O}(\sigma d \sqrt{T} + d r \sqrt{\mathrm{Tr}(\Sigma_0)})$ Bayesian regret in the linear-Gaussian bandit with a $\mathcal{N}(\mu_0, \Sigma_0)$ prior distribution on the coefficient…
arXiv:2607.02891v1 Announce Type: cross Abstract: Many online decision-making problems involve both round-specific feasible actions and drifting reward models: eligible ad impressions, feasible prices, and available treatments can change over time, while user preferences, demand …
arXiv:2510.03798v3 Announce Type: replace-cross Abstract: The batched multi-armed bandit (MAB) problem, where rewards are collected in batches, is pivotal in applications like clinical trials. While prior work assumes light-tailed reward distributions, real-world scenarios often …
Many online decision-making problems involve both round-specific feasible actions and drifting reward models: eligible ad impressions, feasible prices, and available treatments can change over time, while user preferences, demand curves, and patient responses may evolve. Motivate…
