arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2010.03082cs.LG
收藏

多提示在线线性优化

Online Linear Optimization with Many Hints

University of Utah(犹他大学);Google Research(谷歌研究院);Boston University(波士顿大学)

Aditya Bhaskara, Ashok Cutkosky, Ravi Kumar, Manish Purohit

摘要:

我们研究了一个在线线性优化(OLO)问题,在该问题中,学习者在做出决定之前,在每一轮都可以访问$K$“提示”向量。在这种情况下,我们设计了一个算法,获得对数遗憾时,存在一个凸组合的$K$提示,具有正相关的成本向量。这显著地扩展了只考虑$K=1$情况的先前工作。为了实现这一点,我们开发了一种方法来结合许多任意OLO算法,以获得遗憾只有一个数学上比最小遗憾的原始算法事后诸葛亮的因素,这一结果是独立的利益。

英文摘要:

We study an online linear optimization (OLO) problem in which the learner is provided access to $K$ "hint" vectors in each round prior to making a decision. In this setting, we devise an algorithm that obtains logarithmic regret whenever there exists a convex combination of the $K$ hints that has positive correlation with the cost vectors. This significantly extends prior work that considered only the case $K=1$. To accomplish this, we develop a way to combine many arbitrary OLO algorithms to obtain regret only a logarithmically worse factor than the minimum regret of the original algorithms in hindsight; this result is of independent interest.

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。

↑