Distributed Learning of Distributions via Social Sampling
Distributed Learning of Distributions via Social Sampling
复制标题
DOI：
10.1109/tac.2014.2329611
复制
发表时间：
2013-05
影响因子：
6.8
通讯作者：
A. Sarwate;T. Javidi
中科院分区：
文献类型：
--
作者：
A. Sarwate;T. Javidi
提出了一种离散分布的分布式估计协议。每个代理从分布中的单个样本开始，目标是学习样本的经验分布。该协议是基于一个简单的消息传递模型的动机在社交网络的通信。代理从其当前的分布估计中随机抽取消息，从而产生具有量化消息的协议。使用随机逼近的工具，该算法几乎肯定收敛。例子说明了三种制度与不同的共识现象。仿真证明了这种收敛性，并给出了一些洞察网络拓扑结构的影响。
A protocol for distributed estimation of discrete distributions is proposed. Each agent begins with a single sample from the distribution, and the goal is to learn the empirical distribution of the samples. The protocol is based on a simple message-passing model motivated by communication in social networks. Agents sample a message randomly from their current estimates of the distribution, resulting in a protocol with quantized messages. Using tools from stochastic approximation, the algorithm is shown to converge almost surely. Examples illustrate three regimes with different consensus phenomena. Simulations demonstrate this convergence and give some insight into the effect of network topology.