Social Learning and Distributed Hypothesis Testing

DOI10.1109/TIT.2018.2837050MaRDI QIDQ4682905zbMATH OpenOpenAlexWikidataFDO

Authors Anusha Lalitha, Tara Javidi, Anand Dilip Sarwate

Publication date 19 September 2018

Published in IEEE Transactions on Information Theory (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1410.4307

Mathematics Subject Classification ID

Large deviations (60F10) Statistical aspects of information-theoretic topics (62B10) Parametric hypothesis testing (62F03) Learning and adaptive systems in artificial intelligence (68T05)

Abstract: This paper considers a problem of distributed hypothesis testing and social learning. Individual nodes in a network receive noisy local (private) observations whose distribution is parameterized by a discrete parameter (hypotheses). The conditional distributions are known locally at the nodes, but the true parameter/hypothesis is not known. An update rule is analyzed in which nodes first perform a Bayesian update of their belief (distribution estimate) of the parameter based on their local observation, communicate these updates to their neighbors, and then perform a "non-Bayesian" linear consensus using the log-beliefs of their neighbors. In this paper we show that under mild assumptions, the belief of any node in any incorrect hypothesis converges to zero exponentially fast, and we characterize the exponential rate of learning which is given in terms of the network structure and the divergences between the observations' distributions. Our main result is the concentration property established on the rate of convergence.

Recommendations

• Distributed Hypothesis Testing With Social Learning and Symmetric Fusion
• Distributed Learning of Distributions via Social Sampling
• A distributed learning dynamics in social groups
• Social learning with bounded confidence and heterogeneous agents
• Social Learning With Bayesian Agents and Random Decision Making
• A New Approach to Distributed Hypothesis Testing and Non-Bayesian Learning: Improved Learning Rate and Byzantine Resilience
• Social learning in social networks
• Distributed Hypothesis Testing: Cooperation and Concurrent Detection
• Testing Models of Social Learning on Networks: Evidence From Two Experiments

Cited in

(7)

• Social learning with multiple true states
• Defending non-Bayesian learning against adversarial attacks
• Non-Bayesian social learning model with periodically switching structures
• Graph-theoretic approaches for analyzing the resilience of distributed control systems: a tutorial and survey
• Nonlinear Consensus+Innovations under Correlated Heavy-Tailed Noises: Mean Square Convergence Rate and Asymptotics
• Distributed Recursive Estimation under Heavy-Tail Communication Noise
• Mitigating disinformation in social networks through noise

This page was built for publication: Social Learning and Distributed Hypothesis Testing

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4682905)