Non-Bayesian social learning
From MaRDI portal
Abstract: We study a model of information aggregation and social learning recently proposed by Jadbabaie, Sandroni, and Tahbaz-Salehi, in which individual agents try to learn a correct state of the world by iteratively updating their beliefs using private observations and beliefs of their neighbors. No individual agent's private signal might be informative enough to reveal the unknown state. As a result, agents share their beliefs with others in their social neighborhood to learn from each other. At every time step each agent receives a private signal, and computes a Bayesian posterior as an intermediate belief. The intermediate belief is then averaged with the belief of neighbors to form the individual's belief at next time step. We find a set of minimal sufficient conditions under which the agents will learn the unknown state and reach consensus on their beliefs without any assumption on the private signal structure. The key enabler is a result that shows that using this update, agents will eventually forecast the indefinite future correctly.
Recommendations
- A theory of non-Bayesian social learning
- Non-Bayesian Social Learning With Uncertain Models
- Non-Bayesian updating in a social learning experiment
- Non-Bayesian social learning model with periodically switching structures
- Social Learning With Bayesian Agents and Random Decision Making
- Bayesian social learning with local interactions
- Non-Bayesian learning
- Learning dynamics in social dilemmas
- Social learning equilibria
- scientific article; zbMATH DE number 1189219
Cites work
- scientific article; zbMATH DE number 5819433 (Why is no real title available?)
- scientific article; zbMATH DE number 3760340 (Why is no real title available?)
- scientific article; zbMATH DE number 3087284 (Why is no real title available?)
- Bayesian learning in social networks
- Bayesian learning in social networks.
- Compatible Measures and Merging
- Conformism and diversity under social learning.
- Informational externalities and emergence of consensus
- Iterative maximum likelihood on networks
- Learning from Neighbours
- Non-Bayesian learning
- Pathological Outcomes of Observational Learning
- Persuasion Bias, Social Influence, and Unidimensional Opinions
- Reaching a Consensus
- Spread of (mis)information in social networks
- Weak and strong merging of opinions
- Word-of-Mouth Communication and Social Learning
- Word-of-mouth learning.
Cited in
(76)- Dynamics of information exchange in endogenous social networks
- Social learning in networks with time-varying topologies
- A survey on nonstrategic models of opinion dynamics
- Non-Bayesian social learning model with periodically switching structures
- History-independent distributed multi-agent learning
- Does one Bayesian make a difference?
- Opinion dynamics and learning in social networks
- Opinion dynamics and wisdom under out-group discrimination
- Social learning with multiple true states
- Coordination with local information
- Bayesian decision making in groups is hard
- Non-Bayesian learning
- Graph-theoretic approaches for analyzing the resilience of distributed control systems: a tutorial and survey
- Consensus in social networks: revisited
- Defending non-Bayesian learning against adversarial attacks
- Learning to coordinate in social networks
- Doob's consistency of a non-Bayesian updating process
- Cognitively-constrained learning from neighbors
- Reaching consensus via non-Bayesian asynchronous learning in social networks
- A Reputation Game Simulation: Emergent Social Phenomena from Information Theory
- Virtually additive learning
- Learning Manipulation Through Information Dissemination
- On information distortions in online ratings
- Communication with unknown perspectives
- Theoretical development of a probabilistic fuzzy model for opinion formation in social networks
- Distributed Bayesian filtering using logarithmic opinion pool for dynamic sensor networks
- A model of belief influence in large social networks
- Vacillating about media bias: changing one's mind intermittently within a network of political allies and opponents
- Chaos in social learning with multiple true states
- Social learning with bounded confidence and heterogeneous agents
- Finite-time influence systems and the wisdom of crowd effect
- Social Learning With Bayesian Agents and Random Decision Making
- A theory of non-Bayesian social learning
- The influence of communication structure on opinion dynamics in social networks with multiple true states
- The evolution of beliefs over signed social networks
- Opinion dynamics in networks with common-neighbors-based connections
- Hiding opinions by minimizing disclosed information: an obfuscation-based opinion dynamics model
- The equivalence of two rational expectations equilibrium economies with different approaches to processing neighbors' information
- Opinion dynamics and wisdom under conformity
- Broken detailed balance and non-equilibrium dynamics in noisy social learning models
- Sequential decision aggregation with social pressure
- A framework for studying decentralized Bayesian learning with strategic agents
- Opinion influence and evolution in social networks: a Markovian agents model
- Misinformation due to asymmetric information sharing
- Social learning with time-varying weights
- Iterated learning in dynamic social networks
- Non-Bayesian updating in a social learning experiment
- Towards control of opinion diversity by introducing zealots into a polarised social group
- Rebels lead to the doctrine of the mean: a heterogeneous degroot model
- Linear time average consensus and distributed optimization on fixed graphs
- Information diffusion in networks with the Bayesian peer influence heuristic
- Opinion dynamics of social learning with a conflicting source
- Opinion dynamics of modified Hegselmann-Krause model in a group-based population with heterogeneous bounded confidence
- Collaborative scalar-gain estimators for potentially unstable social dynamics with limited communication
- Online discrete optimization in social networks in the presence of Knightian uncertainty
- On a diversity of perspectives and world views: learning under Bayesian vis-á-vis DeGroot updating
- Confirmation bias in social networks
- Analysis of opinion evolution based on non-Bayesian social learning
- Learning in networks with idiosyncratic agents
- ``Since you're so rich, you must be really smart: talent, rent sharing, and the finance wage premium
- A network solution to robust implementation: the case of identical but unknown distributions
- A more credible approach to parallel trends
- A welfare analysis of occupational licensing in U.S. states
- Hazed and confused: the effect of air pollution on dementia
- IQ, expectations, and choice
- Learning from neighbours about a changing state
- Optimal feedback in contests
- Price discrimination in the information age: prices, poaching, and privacy with personalized targeted discounts
- Save, spend, or give? A model of housing, family insurance, and savings in old age
- Stratification trees for adaptive randomisation in randomised controlled trials
- Testing the production approach to markup estimation
- Unemployment insurance in macroeconomic stabilization
- Dynamic opinion aggregation: long-run stability and disagreement
- A hierarchical decision-making framework in social networks for efficient disaster management
- As strong as the weakest node: the impact of misinformation in social networks
- Granular degroot dynamics -- a model for robust naive learning in social networks
This page was built for publication: Non-Bayesian social learning
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q380872)
