arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.05378cs.LG
收藏

随机线性Bands的特征与参数选择

Feature and Parameter Selection in Stochastic Linear Bandits

University of California, Santa Barbara(加州大学圣巴巴拉分校);DeepMind(深度思维);Google Research(谷歌研究院)

Ahmadreza Moradipari, Berkay Turan, Yasin Abbasi-Yadkori, Mahnoosh Alizadeh, Mohammad Ghavamzadeh

摘要:

研究了随机线性强盗模型中的两种模型选择设置。在第一种设置中,我们称之为特征选择,LB问题的预期回报是在至少一个$M$特征图(模型)的线性跨度中。在第二种设置中,LB问题的奖励参数从表示为$\mathbb R^d$中的(可能)重叠球的$M$模型中任意选择。但是,代理只能访问错误指定的模型,即~球的中心和半径的估计。我们将此设置称为参数选择。对于每一个设置,我们开发和分析一个计算效率高的算法,是基于减少土匪的全信息问题。这使我们能够获得不比真实模型已知的情况更差的后悔界限(直到$\sqrt{\log M}$因子)。这是在这些设置中对模型数量$M$的最佳依赖性。最后,我们经验表明,我们的算法使用合成和真实世界的实验的有效性。

英文摘要:

We study two model selection settings in stochastic linear bandits (LB). In the first setting, which we refer to as feature selection, the expected reward of the LB problem is in the linear span of at least one of $M$ feature maps (models). In the second setting, the reward parameter of the LB problem is arbitrarily selected from $M$ models represented as (possibly) overlapping balls in $\mathbb R^d$. However, the agent only has access to misspecified models, i.e.,~estimates of the centers and radii of the balls. We refer to this setting as parameter selection. For each setting, we develop and analyze a computationally efficient algorithm that is based on a reduction from bandits to full-information problems. This allows us to obtain regret bounds that are not worse (up to a $\sqrt{\log M}$ factor) than the case where the true model is known. This is the best-reported dependence on the number of models $M$ in these settings. Finally, we empirically show the effectiveness of our algorithms using synthetic and real-world experiments.

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。

↑