Technical Program

Paper Detail

Paper IDE.5.4
Paper Title Social Learning with Beliefs in a Parallel Network
Authors Daewon Seo, University of Wisconsin-Madison, United States; Ravi Kiran Raman, Analog Devices, United States; Lav R. Varshney, University of Illinois at Urbana-Champaign, United States
Session E.5: Hypothesis Testing I
Presentation Lecture
Track Detection and Estimation
Manuscript  Click here to download the manuscript
Virtual Presentation  Click here to watch in the Virtual Symposium
Abstract Consider a social learning problem in a parallel network, where N distributed agents make independent selfish binary decisions, and a central agent aggregates them together with a private signal to make a final decision. In particular, all agents have private beliefs for the true prior, based on which they perform binary hypothesis testing. We focus on the Bayes risk of the central agent, and counterintuitively find that a collection of agents with incorrect beliefs could outperform a set of agents with correct beliefs. We also consider many-agent asymptotics (i.e., N is large) when distributed agents all have identical beliefs, for which it is found that the central agent's decision is polarized and beliefs determine the limit value of the central agent's risk. Moreover, it is surprising that when all agents believe a certain prior-agnostic constant belief, it achieves globally optimal risk as N goes to infinity.

Plan Ahead


2021 IEEE International Symposium on Information Theory

11-16 July 2021 | Melbourne, Victoria, Australia

Visit Website!