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 1709.03570math.STstat.TH
收藏

一种适用于大规模众包的KL-LUCB Bandit算法

A KL-LUCB Bandit Algorithm for Large-Scale Crowdsourcing

Bob Mankoff, Robert Nowak, Ervin Tanczos

摘要:

本文研究了有界报酬条件下多臂强盗系统的最佳臂识别问题。我们开发了一个算法,是一个融合的lil-UCB和KL-LUCB,提供最好的质量的两个算法在一个方法。这是通过证明一个新的任何时候都有界分布,这是最近开发的亚高斯分布的LIL型界的模拟的平均置信界。我们证实了我们的理论结果与数值实验的基础上,纽约客卡通字幕比赛。

英文摘要:

This paper focuses on best-arm identification in multi-armed bandits with bounded rewards. We develop an algorithm that is a fusion of lil-UCB and KL-LUCB, offering the best qualities of the two algorithms in one method. This is achieved by proving a novel anytime confidence bound for the mean of bounded distributions, which is the analogue of the LIL-type bounds recently developed for sub-Gaussian distributions. We corroborate our theoretical results with numerical experiments based on the New Yorker Cartoon Caption Contest.

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。

↑