arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1206.6487cs.LGcs.GTstat.ML
收藏

有限随机局部监测的自适应算法

An Adaptive Algorithm for Finite Stochastic Partial Monitoring

University of Alberta(阿尔伯塔大学)

Gabor Bartok, Navid Zolghadr, Csaba Szepesvari

摘要:

我们提出了一个新的任何时候算法,实现近最佳遗憾的任何情况下,有限的随机部分监测。特别是,新算法实现了极大极小遗憾,对数因子内,“容易”和“困难”的问题。对于简单的问题,它还实现了对数个体遗憾。最重要的是,该算法是自适应的意义上说,如果对手的战略是在一个“容易的区域”的战略空间,然后后悔增长,如果问题是容易的。作为一个含义,我们表明,在一些合理的附加假设下,该算法在动态定价中具有O(\sqrt{T})的遗憾,Bartok等人证明了这一点。

英文摘要:

We present a new anytime algorithm that achieves near-optimal regret for any instance of finite stochastic partial monitoring. In particular, the new algorithm achieves the minimax regret, within logarithmic factors, for both "easy" and "hard" problems. For easy problems, it additionally achieves logarithmic individual regret. Most importantly, the algorithm is adaptive in the sense that if the opponent strategy is in an "easy region" of the strategy space then the regret grows as if the problem was easy. As an implication, we show that under some reasonable additional assumptions, the algorithm enjoys an O(\sqrt{T}) regret in Dynamic Pricing, proven to be hard by Bartok et al. (2011).

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。

↑