Non-Bayesian Social Learning with Uncertain Models over Time-Varying Directed Graphs
Name
1909.04255.pdf
Description
Accepted version
Size
573.58 KB
Format
Adobe PDF
Checksum (MD5)
c235e4fb93ef87b7da5265d11d939afb
Author(s)
Uribe, CA
Hare, JZ
Kaplan, L
Jadbabaie, A
Date Issued
December 1, 2019
Journal
Proceedings of the IEEE Conference on Decision and Control
Publisher
IEEE
Citation
Uribe, CA, Hare, JZ, Kaplan, L and Jadbabaie, A. 2019. "Non-Bayesian Social Learning with Uncertain Models over Time-Varying Directed Graphs." Proceedings of the IEEE Conference on Decision and Control, 2019-December.
Version
Author's final manuscript
Abstract
© 2019 IEEE. We study the problem of non-Bayesian social learning with uncertain models, in which a network of agents seek to cooperatively identify the state of the world based on a sequence of observed signals. In contrast with the existing literature, we focus our attention on the scenario where the statistical models held by the agents about possible states of the world are built from finite observations. We show that existing non-Bayesian social learning approaches may select a wrong hypothesis with non-zero probability under these conditions. Therefore, we propose a new algorithm to iteratively construct a set of beliefs that indicate whether a certain hypothesis is supported by the empirical evidence. This new algorithm can be implemented over time-varying directed graphs, with non-doubly stochastic weights.
MIT Department
Massachusetts Institute of Technology. Institute for Data, Systems, and Society
Massachusetts Institute of Technology. Department of Civil and Environmental Engineering
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1109/CDC40024.2019.9029547
