arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.09626cs.LGstat.ML
收藏

高维Bandit问题的一个简单统一框架

A Simple Unified Framework for High Dimensional Bandit Problems

Purdue University(普渡大学)

Wenjie Li, Adarsh Barik, Jean Honorio

摘要:

具有低维结构的随机高维强盗问题在不同的应用中是有用的,例如在线广告和药物发现。在这项工作中,我们提出了一个简单的统一算法,这样的问题,并提出了一个通用的分析框架,我们的算法的遗憾上限。我们表明,在一些温和的统一假设下,我们的算法可以适用于不同的高维强盗问题。我们的框架利用低维结构来指导问题中的参数估计,因此我们的算法在LASSO强盗中实现了可比较的遗憾界,以及在低秩矩阵强盗,组稀疏矩阵强盗和一个新的问题:多智能体LASSO强盗中实现了新的界。

英文摘要:

Stochastic high dimensional bandit problems with low dimensional structures are useful in different applications such as online advertising and drug discovery. In this work, we propose a simple unified algorithm for such problems and present a general analysis framework for the regret upper bound of our algorithm. We show that under some mild unified assumptions, our algorithm can be applied to different high dimensional bandit problems. Our framework utilizes the low dimensional structure to guide the parameter estimation in the problem, therefore our algorithm achieves the comparable regret bounds in the LASSO bandit, as well as novel bounds in the low-rank matrix bandit, the group sparse matrix bandit, and in a new problem: the multi-agent LASSO bandit.

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。

↑