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 2202.11795cs.LGcs.AI
收藏

利用相关性提高低等级偏好强盗的学习率

Exploiting Correlation to Achieve Faster Learning Rates in Low-Rank Preference Bandits

University of Michigan(密歇根大学);Microsoft Research(微软研究院)

Suprovat Ghoshal, Aadirupa Saha

摘要:

我们介绍了\emph{Correlated Preference Bandits}问题与随机效用为基础的选择模型(RUM),其目标是确定最好的项目从一个给定的池$n$项目通过在线subsetwise偏好反馈。我们研究了具有简单相关结构的模型,例如低秩模型,是否可以导致更快的学习率。虽然我们表明,这个问题可能是不可能解决的一般“低排名”的选择模型,更快的学习率可以达到假设更多的结构化项目的相关性。特别是,我们介绍了一类新的\emph{Block-Rank}基于RUM模型,其中最好的项目是$(ε,δ)$ -PAC学习只有$O(r ε^{-2} \log(n/δ))$的样本。这改进了通常学习算法已知的$\tilde{O}(nε^{-2} \log(1/δ))$的标准样本复杂度界限,通常学习算法可能不利用项目相关性($r \ll n$)。我们补充了上述样本的复杂性与匹配的下限(对数因子),证明我们的分析的紧密性。令人惊讶的是,我们还显示了一个下界的$Ω(nε^{-2}\log(1/δ))$时,学习者被迫发挥只是决斗,而不是更大的subsetwise查询。此外,我们将结果扩展到更一般的“\emph{noisy Block-Rank}”模型,这确保了我们的技术的鲁棒性。总的来说,我们的研究结果证明了优势,发挥subsetwise查询成对的偏好$(k=2)$,我们证明了后者未能利用相关性。

英文摘要:

We introduce the \emph{Correlated Preference Bandits} problem with random utility-based choice models (RUMs), where the goal is to identify the best item from a given pool of $n$ items through online subsetwise preference feedback. We investigate whether models with a simple correlation structure, e.g. low rank, can result in faster learning rates. While we show that the problem can be impossible to solve for the general `low rank' choice models, faster learning rates can be attained assuming more structured item correlations. In particular, we introduce a new class of \emph{Block-Rank} based RUM model, where the best item is shown to be $(ε,δ)$-PAC learnable with only $O(r ε^{-2} \log(n/δ))$ samples. This improves on the standard sample complexity bound of $\tilde{O}(nε^{-2} \log(1/δ))$ known for the usual learning algorithms which might not exploit the item-correlations ($r \ll n$). We complement the above sample complexity with a matching lower bound (up to logarithmic factors), justifying the tightness of our analysis. Surprisingly, we also show a lower bound of $Ω(nε^{-2}\log(1/δ))$ when the learner is forced to play just duels instead of larger subsetwise queries. Further, we extend the results to a more general `\emph{noisy Block-Rank}' model, which ensures robustness of our techniques. Overall, our results justify the advantage of playing subsetwise queries over pairwise preferences $(k=2)$, we show the latter provably fails to exploit correlation.

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。

↑