论文标题
沟通高效的协作最佳手臂识别
Communication-Efficient Collaborative Best Arm Identification
论文作者
论文摘要
我们在多项式学习模型中调查了Top-$ m $ ARM标识，这是Bandit理论中的一个基本问题，在该模型中，代理商协作以学习目标函数。我们有兴趣设计使用最低通信成本的协作学习算法，以实现最大的加速（与单人学习算法相比），因为沟通通常是多项式学习中的瓶颈。我们提供算法和不可能的结果，并进行一组实验以证明我们的算法的有效性。
We investigate top-$m$ arm identification, a basic problem in bandit theory, in a multi-agent learning model in which agents collaborate to learn an objective function. We are interested in designing collaborative learning algorithms that achieve maximum speedup (compared to single-agent learning algorithms) using minimum communication cost, as communication is frequently the bottleneck in multi-agent learning. We give both algorithmic and impossibility results, and conduct a set of experiments to demonstrate the effectiveness of our algorithms.
