arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1610.04578stat.MLcs.LG
收藏

一种改进的强自适应硬币投注在线学习算法

Improved Strongly Adaptive Online Learning using Coin Betting

UW-Madison(威斯康星大学麦迪逊分校);Stony Brook University(纽约州立大学石溪分校)

Kwang-Sung Jun, Francesco Orabona, Rebecca Willett, Stephen Wright

摘要:

本文提出了一种新的无参数的在线学习算法,以适应不断变化的环境。在与我们的算法具有相同的时间复杂度相比,我们得到了一个强自适应遗憾界,是一个因素,至少$\sqrt{\log(T)}$更好,其中$T$是时间范围。实验结果表明,我们的算法优于国家的最先进的方法在学习专家的意见和度量学习的情况下。

英文摘要:

This paper describes a new parameter-free online learning algorithm for changing environments. In comparing against algorithms with the same time complexity as ours, we obtain a strongly adaptive regret bound that is a factor of at least $\sqrt{\log(T)}$ better, where $T$ is the time horizon. Empirical results show that our algorithm outperforms state-of-the-art methods in learning with expert advice and metric learning scenarios.

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。

↑