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 1802.07176cs.LGstat.ML
收藏

自适应采样的粗排序

Adaptive Sampling for Coarse Ranking

Sumeet Katariya, Lalit Jain, Nandana Sengupta, James Evans, Robert Nowak

摘要:

我们考虑主动粗排名的问题,其中的目标是排序项目根据其手段到集群的预先指定的大小,通过自适应采样从他们的奖励分布。此设置在许多涉及人类评分员的社会科学应用中非常有用,并且需要每个项目的近似排名。与找到精确排名所需的数量相比,近似或粗略排名可以显著减少所需的评级数量。我们提出了一个计算效率高的PAC算法LUCBRank的粗排名,并推导出其样本复杂度的上限。我们还得到了一个几乎匹配的分布相关的下界。对合成数据和真实数据的实验表明,LUCBRank的性能优于最先进的基线方法,即使这些方法具有了解底层参数模型的优势。

英文摘要:

We consider the problem of active coarse ranking, where the goal is to sort items according to their means into clusters of pre-specified sizes, by adaptively sampling from their reward distributions. This setting is useful in many social science applications involving human raters and the approximate rank of every item is desired. Approximate or coarse ranking can significantly reduce the number of ratings required in comparison to the number needed to find an exact ranking. We propose a computationally efficient PAC algorithm LUCBRank for coarse ranking, and derive an upper bound on its sample complexity. We also derive a nearly matching distribution-dependent lower bound. Experiments on synthetic as well as real-world data show that LUCBRank performs better than state-of-the-art baseline methods, even when these methods have the advantage of knowing the underlying parametric model.

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。

↑