Sarwate, Anand D. & Javidi, Tara (2015). Distributed Learning of Distributions via Social Sampling. IEEE Transactions on Automatic Control, 60(1), 34-45. Retrieved from https://doi.org/doi:10.7282/T3H70HJJ
AbstractA 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.
SubjectsDistributions, Telecommunication--Message processing, Social sampling
RightsCopyright for scholarly resources published in RUcore is retained by the copyright holder. By virtue of its appearance in this open access medium, you are free to use this resource, with proper attribution, in educational and other non-commercial settings. Other uses, such as reproduction or republication, may require the permission of the copyright holder.