arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1002.0747stat.APcs.LGstat.ML
收藏

基于高斯估计的社交网络贝叶斯学习算法

Efficient Bayesian Learning in Social Networks with Gaussian Estimators

University of Pennsylvania(宾夕法尼亚大学);U.C. Berkeley(加州大学伯克利分校);California Institute of Technology(加州理工学院)

Elchanan Mossel, Noah Olsman, Omer Tamuz

摘要:

我们考虑一组贝叶斯代理谁试图估计的世界状态$θ$通过在社交网络上的互动。每个代理$v$最初接收$θ$的私有测量:从具有平均值$θ$和标准差1的高斯分布中挑选的数字$S_v$。然后,在每个离散时间迭代中,每个都向其邻居揭示其$θ$的估计,并且观察其邻居的动作,使用贝叶斯定律更新其信念。这个过程有效地聚集了信息,在这个意义上,所有的代理人都收敛到他们会有的信念,如果他们能够访问所有的私人测量。我们表明,这个过程是计算效率,使每个代理的计算可以很容易地进行。我们还表明,在任何图的过程收敛后,在最多$2N \cdot D$步骤,其中$N$是代理的数量和$D$是网络的直径。最后,我们表明,在树上和距离传递图的过程收敛后,$D$步骤,它保留隐私,使代理学习很少的私人信号的大多数其他代理,尽管有效的信息聚合。我们的研究结果扩展了第一和最后一位作者未发表的手稿。

英文摘要:

We consider a group of Bayesian agents who try to estimate a state of the world $θ$ through interaction on a social network. Each agent $v$ initially receives a private measurement of $θ$: a number $S_v$ picked from a Gaussian distribution with mean $θ$ and standard deviation one. Then, in each discrete time iteration, each reveals its estimate of $θ$ to its neighbors, and, observing its neighbors' actions, updates its belief using Bayes' Law. This process aggregates information efficiently, in the sense that all the agents converge to the belief that they would have, had they access to all the private measurements. We show that this process is computationally efficient, so that each agent's calculation can be easily carried out. We also show that on any graph the process converges after at most $2N \cdot D$ steps, where $N$ is the number of agents and $D$ is the diameter of the network. Finally, we show that on trees and on distance transitive-graphs the process converges after $D$ steps, and that it preserves privacy, so that agents learn very little about the private signal of most other agents, despite the efficient aggregation of information. Our results extend those in an unpublished manuscript of the first and last authors.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑