TY - GEN
T1 - Gaussian Learning-Without-Recall in a dynamic social network
AU - Wang, Chu
AU - Chazelle, Bernard
N1 - Publisher Copyright:
© 2017 American Automatic Control Council (AACC).
PY - 2017/6/29
Y1 - 2017/6/29
N2 - 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 outdegree 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.
AB - 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 outdegree 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.
UR - http://www.scopus.com/inward/record.url?scp=85027076851&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85027076851&partnerID=8YFLogxK
U2 - 10.23919/ACC.2017.7963747
DO - 10.23919/ACC.2017.7963747
M3 - Conference contribution
AN - SCOPUS:85027076851
T3 - Proceedings of the American Control Conference
SP - 5109
EP - 5114
BT - 2017 American Control Conference, ACC 2017
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2017 American Control Conference, ACC 2017
Y2 - 24 May 2017 through 26 May 2017
ER -