arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1708.01744cs.LG
收藏

离散序列预测中转移专家的集结策略

An aggregating strategy for shifting experts in discrete sequence prediction

Indian Institute of Technology, Madras(印度理工学院马德拉斯分校)

Vishnu Raj, Sheetal Kalyani

摘要:

我们研究了如何在多个专家的建议下使预测器适应非平稳环境。我们研究的问题完全反馈时,最好的专家随着时间的推移,从决策理论的角度来看。该算法是基于流行的指数加权方法与指数折扣。我们提供的理论结果约束下的指数折扣设置后悔。对有限时间问题,给出了后悔概率的上界。不同的现实生活中的数据集的数值验证提供了所提出的算法的实用性。

英文摘要:

We study how we can adapt a predictor to a non-stationary environment with advises from multiple experts. We study the problem under complete feedback when the best expert changes over time from a decision theoretic point of view. Proposed algorithm is based on popular exponential weighing method with exponential discounting. We provide theoretical results bounding regret under the exponential discounting setting. Upper bound on regret is derived for finite time horizon problem. Numerical verification of different real life datasets are provided to show the utility of proposed algorithm.

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。

↑