Social Learning under Randomized Collaborations
Multiagent Systems
2022-05-13 v2 Social and Information Networks
Signal Processing
Abstract
We study a social learning scheme where at every time instant, each agent chooses to receive information from one of its neighbors at random. We show that under this sparser communication scheme, the agents learn the truth eventually and the asymptotic convergence rate remains the same as the standard algorithms which use more communication resources. We also derive large deviation estimates of the log-belief ratios for a special case where each agent replaces its belief with that of the chosen neighbor.
Cite
@article{arxiv.2201.10957,
title = {Social Learning under Randomized Collaborations},
author = {Yunus Inan and Mert Kayaalp and Emre Telatar and Ali H. Sayed},
journal= {arXiv preprint arXiv:2201.10957},
year = {2022}
}
Comments
Accepted for ISIT 2022