Fair Algorithms for Infinite and Contextual Bandits
Fair Algorithms for Infinite and Contextual Bandits
复制标题
无限和上下文强盗的公平算法
DOI：
--
复制
发表时间：
2016
期刊：
影响因子：
--
通讯作者：
Aaron Roth
中科院分区：
文献类型：
--
作者：
Matthew Joseph;Michael Kearns;Jamie Morgenstern;Seth Neel;Aaron Roth
我们研究线性匪徒问题的公平性。从Joseph等人引入的精英公平概念开始。 [2016]，我们对更普遍的问题进行了更精致的分析，通过对可用选择的数量和结构以及所选的数字进行更少的建模假设，可实现更好的性能保证。我们还分析了以前未研究的无限线性匪徒问题中的公平性问题，获得了依赖实例的遗憾上限以及下限，表明这种实例依赖性是必要的。结果是在在线线性环境中具有精英公平性的框架，在线线性环境中，它比当前的艺术状态更强大，一般和现实。
We study fairness in linear bandit problems. Starting from the notion of meritocratic fairness introduced in Joseph et al. [2016], we carry out a more refined analysis of a more general problem, achieving better performance guarantees with fewer modelling assumptions on the number and structure of available choices as well as the number selected. We also analyze the previously-unstudied question of fairness in infinite linear bandit problems, obtaining instance-dependent regret upper bounds as well as lower bounds demonstrating that this instance-dependence is necessary. The result is a framework for meritocratic fairness in an online linear setting that is substantially more powerful, general, and realistic than the current state of the art.