论文标题
强大的异步和与网络无关的合作学习
Robust Asynchronous and Network-Independent Cooperative Learning
论文作者
论文摘要
我们考虑通过分布式非拜访性学习的合作学习模型，在该模型中，一个代理网络试图共同同意一个最能描述一系列本地可用观察结果的假设。在最近提出的薄弱通信网络模型的基础上，我们提出了一项强大的合作学习规则，该规则允许异步通信，消息延迟，不可预测的消息损失以及节点之间的定向通信。我们表明，我们提出的学习动力可以保证网络中的所有代理人都将对他们对错误的假设的信念造成渐近的指数衰减，这表明所有代理人的信念都将集中在最佳假设上。数值实验提供了许多网络设置的证据。
We consider the model of cooperative learning via distributed non-Bayesian learning, where a network of agents tries to jointly agree on a hypothesis that best described a sequence of locally available observations. Building upon recently proposed weak communication network models, we propose a robust cooperative learning rule that allows asynchronous communications, message delays, unpredictable message losses, and directed communication among nodes. We show that our proposed learning dynamics guarantee that all agents in the network will have an asymptotic exponential decay of their beliefs on the wrong hypothesis, indicating that the beliefs of all agents will concentrate on the optimal hypotheses. Numerical experiments provide evidence on a number of network setups.
