To refer to this page use:
|Abstract:||We analyze the dynamics of the Learning-Without-Recall model with Gaussian priors in a dynamic social network. Agents seeking to learn the state of the world, the 'truth', exchange signals about their current beliefs across a changing network and update them accordingly. The agents are assumed memoryless and rational, meaning that they Bayes-update their beliefs based on current states and signals, with no other information from the past. The other assumption is that each agent hears a noisy signal from the truth at a frequency bounded away from zero. Under these conditions, we show that the system reaches truthful consensus almost surely with a convergence rate that is polynomial in expectation. Somewhat paradoxically, high out degree can slow down the learning process. The lower-bound assumption on the truth-hearing frequency is necessary: even infinitely frequent access to the truth offers no guarantee of truthful consensus in the limit.|
|Electronic Publication Date:||3-Jul-2017|
|Citation:||Wang, C, Chazelle, B. (2017). Gaussian Learning-Without-Recall in a dynamic social network. 5109 - 5114. doi:10.23919/ACC.2017.7963747|
|Pages:||5109 - 5114|
|Type of Material:||Conference Article|
|Journal/Proceeding Title:||Proceedings of the American Control Conference|
Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.