论文标题
关于分布式推理的信念的算术和几何融合
On the Arithmetic and Geometric Fusion of Beliefs for Distributed Inference
论文作者
论文摘要
我们研究了分布式假设测试问题中信仰向量的线性和对数线性组合规则下的渐近学习率。我们表明，在两种组合策略下，代理都能够以拟定的速度在对数线性融合下的速度更快地学习真相。我们检查了网络连接性和信息多样性的速率之间的差距。我们还为涉及联合体系结构和可交换网络的特殊情况提供了封闭式表达式。
We study the asymptotic learning rates under linear and log-linear combination rules of belief vectors in a distributed hypothesis testing problem. We show that under both combination strategies, agents are able to learn the truth exponentially fast, with a faster rate under log-linear fusion. We examine the gap between the rates in terms of network connectivity and information diversity. We also provide closed-form expressions for special cases involving federated architectures and exchangeable networks.
