arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2602.14474cs.LG
收藏

一个可靠来源即可:在异质噪声下的带宽问题近最优遗憾

One Good Source is All You Need: Near-Optimal Regret for Bandits under Heterogeneous Noise

Amith Bhat, Haipeng Luo, Aadirupa Saha

AI总结:

本文提出SOAR算法,在异质噪声下实现近最优遗憾,通过快速修剪高方差来源和平衡min-max LCB-UCB方法,取得实例依赖的最优遗憾界。

摘要:

我们研究具有M个异质数据源的K臂多臂老虎机(MAB)问题,每个数据源具有未知且不同的噪声方差{σ_j^2}。学习者的目的是最小化标准MAB遗憾,同时适应性地选择每个回合查询的数据源。我们提出Source-Optimistic Adaptive Regret minimization(SOAR)算法,通过尖锐的方差集中界快速修剪高方差来源,随后采用平衡的min-max LCB-UCB方法,无缝整合识别最佳臂和最优(最小方差)数据源的并行任务。我们的分析显示SOAR取得实例依赖的遗憾界为~O(σ*^2Σ_{i=2}^K log T/Δ_i + sqrt(KΣ_{j=1}^M σ_j^2)),其中σ*^2 := min_j σ_j^2是最小源方差,Δ_i表示第i个臂的次优差距。该结果令人惊讶,尽管缺乏对M个替代源中最小方差源的先验知识,SOAR仍能取得标准单源MAB的最优实例依赖遗憾,同时仅引入小的(不可避免的)加性成本~O(sqrt(KΣ_{j=1}^M σ_j^2))。我们的理论界限在某些提出的基础上有显著改进,例如均匀UCB或探索后提交UCB,这些方法可能面临遗憾缩放与σ_max^2而非σ*^2的差距,当σ_max >> σ*时,这种差距可以任意大。在多个合成问题实例和现实世界MovieLens 25M数据集上的实验显示SOAR在基线上的优越性能。

英文摘要:

We study $K$-armed Multiarmed Bandit (MAB) problem with $M$ heterogeneous data sources, each exhibiting unknown and distinct noise variances $\{σ_j^2\}_{j=1}^M$. The learner's objective is standard MAB regret minimization, with the additional complexity of adaptively selecting which data source to query from at each round. We propose Source-Optimistic Adaptive Regret minimization (SOAR), a novel algorithm that quickly prunes high-variance sources using sharp variance-concentration bounds, followed by a `balanced min-max LCB-UCB approach' that seamlessly integrates the parallel tasks of identifying the best arm and the optimal (minimum-variance) data source. Our analysis shows SOAR achieves an instance-dependent regret bound of $\tilde{O}\left({σ^*}^2\sum_{i=2}^K \frac{\log T}{Δ_i} + \sqrt{K \sum_{j=1}^M σ_j^2}\right)$, up to preprocessing costs depending only on problem parameters, where ${σ^*}^2 := \min_j σ_j^2$ is the minimum source variance and $Δ_i$ denotes the suboptimality gap of the $i$-th arm. This result is both surprising as despite lacking prior knowledge of the minimum-variance source among $M$ alternatives, SOAR attains the optimal instance-dependent regret of standard single-source MAB with variance ${σ^*}^2$, while incurring only an small (and unavoidable) additive cost of $\tilde O(\sqrt{K \sum_{j=1}^M σ_j^2})$ towards the optimal (minimum variance) source identification. Our theoretical bounds represent a significant improvement over some proposed baselines, e.g. Uniform UCB or Explore-then-Commit UCB, which could potentially suffer regret scaling with $σ_{\max}^2$ in place of ${σ^*}^2$-a gap that can be arbitrarily large when $σ_{\max} \gg σ^*$. Experiments on multiple synthetic problem instances and the real-world MovieLens\;25M dataset, demonstrating the superior performance of SOAR over the 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。

↑