Non-Bayesian social learning

By Ali Jadbabaie, Pooya Molavi, Alvaro Sandroni, Alireza Tahbaz-Salehi. Games Econ. Behav., 2012

504 citations recorded by the source corpus.

Subfields: Management Science and Operations Research, Statistical and Nonlinear Physics

View Paper: https://www.semanticscholar.org/paper/462777eabfa55ac31d48d2d65e4e0f3d72bce316

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Management Science and Operations Research

In Statistical and Nonlinear Physics

Citations in the corpus

Distributed Detection: Finite-Time Analysis and Impact of Network Topology (2014, methodology): “We now elaborate on several works inspired by the model considered in [18].”
Social learning and distributed hypothesis testing (2014, methodology): “Our work in this paper is directly motivated by [1] in which social learning is achieved via combining Bayesian updates with consensus averaging on the beliefs.”
Defending non-Bayesian learning against adversarial attacks (2016, unknown): “It is shown [3] that, under this learning rule, each agent learns the true state almost surely.”
Defending Distributed Systems Against Adversarial Attacks: Consensus, Consensusbased Learning, and Statistical Learning (2020, methodology): “(2) Non-Bayesian Learning: To avoid the complexity of Bayesian learning, an approximate Bayesian learning framework in networks, referred to as Non-Bayesian Learning, was proposed [7].”
Linear Time Average Consensus on Fixed Graphs and Implications for Decentralized Optimization and Multi-Agent Control (2014, unknown): “…we mention recent work on coverage control [25], formation control [64, 65], distributed estimation [85, 86, 24, 19, 74], cooperative learning [36], and Kalman ﬁltering [15, 77, 2], distributed task assignment [20], and distributed optimization [82, 57]; these papers and others design…”
Nonasymptotic convergence rates for cooperative learning over time-varying directed graphs (2014, methodology): “In [8], the almost sure convergence of a non-Bayesian rule based on arithmetic mean is shown for a fixed topology graph.”
A tutorial on modeling and analysis of dynamic social networks. Part I (2017, methodology): “The French-DeGroot’s model was independently proposed by Lehrer and Wagner [77, 78, 88] as a model of “rational consensus”; it is often considered as an algorithm of non-Bayesian learning [11, 89, 90].”
Networks, Shocks, and Systemic Risk (2015, background): “Relatedly, Jadbabaie et al. (2012, 2013) show that the rate of information aggregation in a social network is more sensitive to the quality of the signals observed by the more central agents.17”
Information Heterogeneity and the Speed of Learning in Social Networks (2013, methodology): “The DeGroot model is generalized by Jadbabaie et al. (2012) to allow for constant arrival of new information over time.”