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 2306.09136cs.LGstat.ML
收藏

有限时间对数 Bayes 遗憾上界

Finite-Time Logarithmic Bayes Regret Upper Bounds

University of Texas, Austin(德克萨斯大学奥斯汀分校);AWS AI Labs(亚马逊云科技人工智能实验室);Amazon(亚马逊)

Alexia Atsidakou, Branislav Kveton, Sumeet Katariya, Constantine Caramanis, Sujay Sanghavi

AI总结:

本文为 Bayesian bandits 建立首批有限时间对数 Bayes 遗憾上界,并将技术推广到 linear bandits,显著改进既有 $\tilde{O}(\sqrt{n})$ 结果。

摘要:

我们推导了 Bayesian bandits 的首批有限时间对数 Bayes 遗憾上界。在多臂 bandit 中,我们针对一种 upper confidence bound 算法获得了 $O(c_Δ\log n)$ 和 $O(c_h \log^2 n)$ 上界,其中 $c_h$ 和 $c_Δ$ 分别是依赖于先验分布以及从该先验采样的 bandit 实例的差距的常数。后一个界在渐近意义上与 Lai(1987)的下界相匹配。我们的证明在技术上与以往工作有重大偏离,同时简单且通用。为展示我们技术的通用性,我们将其应用于 linear bandits。我们的结果揭示了 Bayesian 设置中先验的价值,既体现在目标中,也体现在提供给学习器的辅助信息中。它们显著改进了现有的 $\tilde{O}(\sqrt{n})$ 界;尽管存在 Lai(1987)的对数下界,这些界仍已成为文献中的标准。

英文摘要:

We derive the first finite-time logarithmic Bayes regret upper bounds for Bayesian bandits. In a multi-armed bandit, we obtain $O(c_Δ\log n)$ and $O(c_h \log^2 n)$ upper bounds for an upper confidence bound algorithm, where $c_h$ and $c_Δ$ are constants depending on the prior distribution and the gaps of bandit instances sampled from it, respectively. The latter bound asymptotically matches the lower bound of Lai (1987). Our proofs are a major technical departure from prior works, while being simple and general. To show the generality of our techniques, we apply them to linear bandits. Our results provide insights on the value of prior in the Bayesian setting, both in the objective and as a side information given to the learner. They significantly improve upon existing $\tilde{O}(\sqrt{n})$ bounds, which have become standard in the literature despite the logarithmic lower bound of Lai (1987).

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。

↑