论文标题
通用线性匪徒的沟通有效的联合学习
Communication Efficient Federated Learning for Generalized Linear Bandits
论文作者
论文摘要
最近在联合学习设置下研究了上下文强盗算法，以满足保持数据分散并将强盗模型的学习推向客户端的需求。但是，受所需的通信效率的限制，现有的解决方案仅限于线性模型，以利用其封闭形式的解决方案进行参数估计。这样的限制模型选择极大地阻碍了这些算法的实用性。在本文中，我们迈出了第一步，通过研究联合学习设置下的广义线性匪徒模型来应对这一挑战。我们提出了一个通信效率的解决方案框架，该框架采用在线回归进行本地更新和离线回归进行全局更新。我们严格证明，尽管设置更加笼统和具有挑战性，但我们的算法可以达到后悔和沟通成本的次线性率，这也通过我们广泛的经验评估来验证。
Contextual bandit algorithms have been recently studied under the federated learning setting to satisfy the demand of keeping data decentralized and pushing the learning of bandit models to the client side. But limited by the required communication efficiency, existing solutions are restricted to linear models to exploit their closed-form solutions for parameter estimation. Such a restricted model choice greatly hampers these algorithms' practical utility. In this paper, we take the first step to addressing this challenge by studying generalized linear bandit models under the federated learning setting. We propose a communication-efficient solution framework that employs online regression for local update and offline regression for global update. We rigorously proved, though the setting is more general and challenging, our algorithm can attain sub-linear rate in both regret and communication cost, which is also validated by our extensive empirical evaluations.
