arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1611.00829cs.DScs.LG
收藏

用于上下文决策的多维二分搜索

Multidimensional Binary Search for Contextual Decision-Making

NYU(纽约大学);Google Research NY(谷歌研究院纽约);MIT(麻省理工学院)

Ilan Lobel, Renato Paes Leme, Adrian Vladu

摘要:

我们考虑一个多维的搜索问题,是出于上下文决策的问题,如动态定价和个性化医疗。大自然从一个$d$维单位球中选择一个状态,然后生成一系列$d$维方向。我们可以访问方向,但不能访问国家。在接收到方向之后,我们必须猜测状态和方向之间的点积的值。我们的目标是尽量减少我们的猜测与真实答案相差超过$ε$的次数。我们构造了一个多项式时间算法,我们称之为投影体积实现遗憾$O(d\log(d/ε))$,这是最佳的$\log d$因素。该算法结合了体切割策略与一种新的几何技术,我们称之为圆柱化。

英文摘要:

We consider a multidimensional search problem that is motivated by questions in contextual decision-making, such as dynamic pricing and personalized medicine. Nature selects a state from a $d$-dimensional unit ball and then generates a sequence of $d$-dimensional directions. We are given access to the directions, but not access to the state. After receiving a direction, we have to guess the value of the dot product between the state and the direction. Our goal is to minimize the number of times when our guess is more than $ε$ away from the true answer. We construct a polynomial time algorithm that we call Projected Volume achieving regret $O(d\log(d/ε))$, which is optimal up to a $\log d$ factor. The algorithm combines a volume cutting strategy with a new geometric technique that we call cylindrification.

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。

↑