Information Heterogeneity and the Speed of Learning in Social Networks
By Ali Jadbabaie, Pooya Molavi, Alireza Tahbaz-Salehi. 2013
116 citations recorded by the source corpus.
Subfields: Management Science and Operations Research, Statistical and Nonlinear Physics
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
- Lili Su
- Shahin Shahrampour
- Tara Javidi
- Anusha Lalitha
- Daron Acemoglu
- Nitin H. Vaidya
- Ali Jadbabaie
- Asuman E. Ozdaglar
In Statistical and Nonlinear Physics
- Lili Su
- Anusha Lalitha
- Tara Javidi
- Daron Acemoglu
- Nitin H. Vaidya
- Alexander Olshevsky
- Asuman E. Ozdaglar
- Alexander Rakhlin
Citations in the corpus
- Peer-to-peer Federated Learning on Graphs (2019, background): “, 2005), and distributed hypothesis testing (Jadbabaie et al., 2013; Nedić et al., 2015; Shahrampour et al., 2016; Lalitha et al., 2018).”
- Defending non-Bayesian learning against adversarial attacks (2016, positive): “we are able to obtain the asymptotic rate O(exp (−Ct)) (using the derivation in the proof of Lemma 3) which is similar to that in the failure-free setting [12,15,16].”
- Social learning and distributed hypothesis testing (2014, result): “A more recent paper [3], strengthens these results by characterizing the “learning rate” of the algorithm.”
- 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”
- Distributed Detection: Finite-Time Analysis and Impact of Network Topology (2014, background): “We also remark that the asymptotic rate of I(θ1, θ2) was also discovered in [19], [21], and [24] for the updates under study.”
- Learning via active hypothesis testing over networks (2017, result): “This work and analysis is closely related and complimentary to a growing body of literature on distributed passive hypothesis testing and parameter estimation [6], [7], [8], [9].”
- Nonasymptotic convergence rates for cooperative learning over time-varying directed graphs (2014, background): “Extensions to information heterogeneity and asymptotic convergence rates have been derived as well [13].”