no code implementations • 8 Jan 2023 • Mohammad Esmaeili, Aria Nosratinia
We analyze the conditions for exact recovery when these auxiliary latent variables are unknown, representing unknown nuisance parameters or model mismatch.
1 code implementation • 6 May 2021 • Mohammad Esmaeili, Hussein Metwaly Saad, Aria Nosratinia
SDP is an efficient solution for standard community detection on graphs.
no code implementations • 8 Feb 2021 • Mohammad Esmaeili, Aria Nosratinia
In community detection, the exact recovery of communities (clusters) has been mainly investigated under the general stochastic block model with edges drawn from Bernoulli distributions.
1 code implementation • 29 Sep 2020 • Mohammad Esmaeili, Aria Nosratinia
Another contribution of this paper is relevant to non-graph observations (independent side information) that exists beside a graph realization in many applications.
no code implementations • 8 Jan 2019 • Hussein Saad, Aria Nosratinia
For two symmetric communities, the asymptotic residual error for belief propagation is calculated under finite-alphabet side information, generalizing a previous result with noisy labels.
no code implementations • 5 Sep 2018 • Hussein Saad, Aria Nosratinia
Under belief propagation, tight necessary and sufficient conditions for weak recovery are calculated when the LLRs are constant, and sufficient conditions when the LLRs vary with $n$.