Social learning and distributed hypothesis testing

By Anusha Lalitha, Anand D. Sarwate, Tara Javidi. 2014

201 citations recorded by the source corpus.

This paper considers a problem of distributed hypothesis testing and social learning. Individual nodes in a network receive noisy (private) observations whose distribution is parameterized by a discrete parameter (hypotheses). The distributions are known locally at the nodes, but the true parameter/hypothesis is not known. An update rule is analyzed in which agents 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. The main result of this paper is that under mild assumptions, the belief of any agent in any incorrect parameter converges to zero exponentially fast, and the exponential rate of learning is a characterized by the network structure and the divergences between the observations' distributions.

How researchers see this paper

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

Citations in the corpus

Decentralized Bayesian Learning over Graphs (2019, positive): “Our theoretical and conceptual contributions are as follows: (i) Our decentralized learning rule generalizes a learning rule considered in the social literature [1–3] by restricting the posterior distribution to a predetermined family of distributions for computational tractability.”
Peer-to-peer Federated Learning on Graphs (2019, methodology): “…in statistics, economics, and operations research and encompasses canonical problems of consensus DeGroot (1974), belief propagation (Olfati-Saber et al., 2005), and distributed hypothesis testing (Jad-babaie et al., 2013; Nedi ´ c et al., 2015; Shahrampour et al., 2016; Lalitha et al., 2018).”
Defending non-Bayesian learning against adversarial attacks (2016, neutral): “esigning and analyzing non-Bayesian learning rules with a particular focus on reﬁning the fusion strategies and analyzing the (asymptotic and/or ﬁnite time) convergence rates of the reﬁned algorithms [10,14,15,16,11,18,17,13]. In this paper we are particularly interested in the log-linear form of th”
Nonasymptotic convergence rates for cooperative learning over time-varying directed graphs (2014, background): “In a simultaneous independent effort, the authors in [18], [19] proposed a similar non-Bayesian learning algorithm where a local Bayes update is followed by a consensus step.”
Why Do Multi-Agent LLM Systems Fail? (2025, unknown): “This process can be likened to a learning study where different agents (this time human annotators) independently collect observations from a shared state space and share their findings with each other to reach a consensus (Lalitha et al., 2018).”
Learning via active hypothesis testing over networks (2017, background): “A detailed overview of the large body of literature for the same is provided in [10].”