Interactions Between Learning and Broadcasting in Wireless Recommendation Systems
Interactions Between Learning and Broadcasting in Wireless Recommendation Systems
复制标题
无线推荐系统中学习和广播之间的交互
DOI：
10.1109/isit.2019.8849556
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Devavrat Shah
中科院分区：
文献类型：
--
作者：
Linqi Song;C. Fragouli;Devavrat Shah
我们考虑需要在无线带宽限制下运行的推荐系统，无线带宽是用广播传输的数量来衡量的。我们展示了在上下文多臂强盗框架中制定的无线建议的遗憾和带宽之间的权衡（在某些情况下很紧张）。
We consider recommendation systems that need to operate under wireless bandwidth constraints, which is measured as the number of broadcast transmissions. We demonstrate a (tight for some instances) tradeoff between regret and bandwidth for wireless recommendations formulated in a contextual multiarmed bandit framework.