arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.02504cs.LGcs.AIstat.ML
收藏

非平稳环境中的 MNL-Bandit

MNL-Bandit in non-stationary environments

Columbia University(哥伦比亚大学);University of Chicago(芝加哥大学)

Ayoub Foussoul, Vineet Goyal, Varun Gupta

AI总结:

该文研究非平稳 MNL-Bandit,基于周期算法提出新估计偏差刻画与集中界,获得匹配上下界的最优最坏情形期望遗憾。

摘要:

本文研究非平稳环境下的 MNL-Bandit 问题,并提出一种算法,其最坏情形期望遗憾为 $\tilde{O}\left( \min \left\{ \sqrt{NTL}\\;,\\; N^{\frac{1}{3}}(\Delta_{\infty}^{K})^{\frac{1}{3}} T^{\frac{2}{3}} + \sqrt{NT}\right\}\right)$。其中,$N$ 表示臂数,$L$ 表示变化次数,$\Delta_{\infty}^{K}$ 是未知参数的一种变化度量。此外,我们给出了期望遗憾的匹配下界(相差至多对数因子),表明该算法是最优的。我们的方法建立在 Agrawal 等人 2016 年针对平稳 MNL-Bandit 的基于周期的算法之上。然而,非平稳性带来若干挑战,因此我们引入新技术和新思路加以应对。特别地,我们对非平稳性在估计量中引入的偏差给出了紧刻画,并推导了新的集中界。

英文摘要:

In this paper, we study the MNL-Bandit problem in a non-stationary environment and present an algorithm with a worst-case expected regret of $\tilde{O}\left( \min \left\{ \sqrt{NTL}\;,\; N^{\frac{1}{3}}(Δ_{\infty}^{K})^{\frac{1}{3}} T^{\frac{2}{3}} + \sqrt{NT}\right\}\right)$. Here $N$ is the number of arms, $L$ is the number of changes and $Δ_{\infty}^{K}$ is a variation measure of the unknown parameters. Furthermore, we show matching lower bounds on the expected regret (up to logarithmic factors), implying that our algorithm is optimal. Our approach builds upon the epoch-based algorithm for stationary MNL-Bandit in Agrawal et al. 2016. However, non-stationarity poses several challenges and we introduce new techniques and ideas to address these. In particular, we give a tight characterization for the bias introduced in the estimators due to non stationarity and derive new concentration bounds.

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。

↑