arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1909.02553stat.MLcs.AIcs.LGmath.OCmath.STstat.TH
收藏

平滑的情境强盗:连接参数和不可微后悔机制

Smooth Contextual Bandits: Bridging the Parametric and Non-differentiable Regret Regimes

Cornell University(康奈尔大学)

Yichun Hu, Nathan Kallus, Xiaojie Mao

摘要:

研究了一个非参数上下文强盗问题,其中期望报酬函数属于具有光滑参数$β$的Hölder类.我们展示了这是如何在两个极端之间进行插值的,这两个极端是以前孤立地研究的:不可微的土匪($β\leq1$),通过在不同的上下文区域运行单独的非上下文土匪来实现速率最优遗憾,和参数响应土匪(满足$β=\infty$),由于无限的外推性,可以实现速率最优遗憾的最小或没有探索。我们开发了一种新的算法,仔细调整到所有的平滑设置,我们证明它的遗憾是率最优的,通过建立匹配的上限和下限,恢复现有的结果在两个极端。从这个意义上说,我们的工作弥合了现有文献之间的差距参数和不可微的上下文土匪问题和土匪算法之间,专门使用全球或本地信息,揭示了关键的相互作用的复杂性和遗憾的上下文土匪。

英文摘要:

We study a nonparametric contextual bandit problem where the expected reward functions belong to a Hölder class with smoothness parameter $β$. We show how this interpolates between two extremes that were previously studied in isolation: non-differentiable bandits ($β\leq1$), where rate-optimal regret is achieved by running separate non-contextual bandits in different context regions, and parametric-response bandits (satisfying $β=\infty$), where rate-optimal regret can be achieved with minimal or no exploration due to infinite extrapolatability. We develop a novel algorithm that carefully adjusts to all smoothness settings and we prove its regret is rate-optimal by establishing matching upper and lower bounds, recovering the existing results at the two extremes. In this sense, our work bridges the gap between the existing literature on parametric and non-differentiable contextual bandit problems and between bandit algorithms that exclusively use global or local information, shedding light on the crucial interplay of complexity and regret in contextual 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。

↑