Algorithmic detectability threshold of the stochastic blockmodel

10/24/2017
by   Tatsuro Kawamoto, et al.
0

The assumption that the values of model parameters are known or correctly learned, i.e., the Nishimori condition, is one of the requirements for the detectability analysis of the stochastic blockmodel in statistical inference. In practice, however, there is no example demonstrating that we can know the model parameters beforehand, and there is no guarantee that the model parameters can be learned accurately. In this study, we consider the expectation-maximization (EM) algorithm with belief propagation (BP) and derive its algorithmic detectability threshold. Our analysis is not restricted to the community structure, but includes general modular structures. Because the algorithm cannot always learn the planted model parameters correctly, the algorithmic detectability threshold is qualitatively different from the one with the Nishimori condition.

READ FULL TEXT

page 10

page 14

research
10/24/2017

Algorithmic infeasibility of community detection in higher-order networks

In principle, higher-order networks that have multiple edge types are mo...
research
05/25/2019

A Projected Non-Linear Conjugate Gradient Algorithm for Destructive Negative Binomial Cure Rate Model

In this paper, we propose a new estimation methodology based on a projec...
research
11/04/2019

Statistical Inference for Model Parameters in Stochastic Gradient Descent via Batch Means

Statistical inference of true model parameters based on stochastic gradi...
research
01/26/2021

Community Detection in the Stochastic Block Model by Mixed Integer Programming

The Degree-Corrected Stochastic Block Model (DCSBM) is a popular model t...
research
06/19/2015

Detectability thresholds and optimal algorithms for community structure in dynamic networks

We study the fundamental limits on learning latent community structure i...
research
06/02/2011

Learning unbelievable marginal probabilities

Loopy belief propagation performs approximate inference on graphical mod...
research
01/22/2021

Towards Expectation-Maximization by SQL in RDBMS

Integrating machine learning techniques into RDBMSs is an important task...

Please sign up or login with your details

Forgot password? Click here to reset