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 1706.00136stat.MLcs.LG
收藏

可扩展的广义线性Bandits:在线计算和散列

Scalable Generalized Linear Bandits: Online Computation and Hashing

UW-Madison(威斯康星大学麦迪逊分校)

Kwang-Sung Jun, Aniruddha Bhargava, Robert Nowak, Rebecca Willett

摘要:

广义线性Bandits(GLB)是随机线性Bandits的自然扩展,近年来得到了广泛的应用。然而,现有的GLB在轮数和臂数方面的规模很差,限制了它们在实践中的实用性。本文提出了新的,可扩展的解决方案,GLB问题在两个方面。首先,不同于现有的GLB,其每时间步长的空间和时间复杂度至少随时间线性增长$t$,我们提出了一个新的算法,执行在线计算,享受恒定的空间和时间复杂度。其核心是一种新的广义线性扩展的在线置信集转换(GLOC方法),它采用\emph{any}在线学习算法,并把它变成一个GLB算法。作为一个特殊的情况下,我们应用GLOC的在线牛顿步算法,这导致在低遗憾GLB算法的时间和内存复杂度比以前的工作低得多。其次,对于手臂的数量$N$是非常大的情况下,我们提出了新的算法,其中每个下一个手臂通过内积搜索选择。这样的方法可以经由散列算法(即,“可散列处理”)并导致$N$中的时间复杂度次线性。虽然GLOC的Thompson采样扩展是散列顺从的,但其针对$d$维臂集的遗憾界与$d^{3/2}$成比例,而GLOC的遗憾界与$d$成比例。为了缩小这一差距,我们提出了一个新的哈希适合的算法,其遗憾界尺度与$d^{5/4}$。最后,我们提出了一种快速近似散列密钥计算(内积),具有比最先进的更好的精度,这可以是独立的利益。我们总结了初步的实验结果,证实了我们的方法的优点。

英文摘要:

Generalized Linear Bandits (GLBs), a natural extension of the stochastic linear bandits, has been popular and successful in recent years. However, existing GLBs scale poorly with the number of rounds and the number of arms, limiting their utility in practice. This paper proposes new, scalable solutions to the GLB problem in two respects. First, unlike existing GLBs, whose per-time-step space and time complexity grow at least linearly with time $t$, we propose a new algorithm that performs online computations to enjoy a constant space and time complexity. At its heart is a novel Generalized Linear extension of the Online-to-confidence-set Conversion (GLOC method) that takes \emph{any} online learning algorithm and turns it into a GLB algorithm. As a special case, we apply GLOC to the online Newton step algorithm, which results in a low-regret GLB algorithm with much lower time and memory complexity than prior work. Second, for the case where the number $N$ of arms is very large, we propose new algorithms in which each next arm is selected via an inner product search. Such methods can be implemented via hashing algorithms (i.e., "hash-amenable") and result in a time complexity sublinear in $N$. While a Thompson sampling extension of GLOC is hash-amenable, its regret bound for $d$-dimensional arm sets scales with $d^{3/2}$, whereas GLOC's regret bound scales with $d$. Towards closing this gap, we propose a new hash-amenable algorithm whose regret bound scales with $d^{5/4}$. Finally, we propose a fast approximate hash-key computation (inner product) with a better accuracy than the state-of-the-art, which can be of independent interest. We conclude the paper with preliminary experimental results confirming the merits of our methods.

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。

↑