O seminário será em inglês.

Speaker:   Guilherme Ost (IM-UFRJ)

Title: Community detection for binary graphical models

April 7, from 3:30 p.m. to 4:30 p.m. (Rio de Janeiro local time)

Room C116 - Bloco C - CT – Instituto de Matemática – UFRJ. 

There will be no transmission online.

Abstract: We consider a system of binary interacting chains describing the dynamics of a group of N individuals that, at each time unit, either send some signal to the others or remain silent otherwise. The interactions among the chains are encoded by a directed Erdös-Rényi random graph with unknown edge probability 0<p<1. Moreover, the system is structured into two communities (excitatory chains versus inhibitory ones) which are coupled via a mean field interaction on the underlying Erdös-Rényi graph. These two communities are also unknown. Last year, I gave a talk at the DME Statistics Seminar discussing how one could estimate the edge probability p based only on the observation of the interacting chains over T time units. In this talk, I will address the complementary question of how to distinguish between the excitatory and inhibitory chains. I will also highlight some of the probabilistics tools we used to tackle this problem. The results presented are based on a joint work with Julien Chevallier (Grenoble).

More complete information about the seminars can be found at

https://ppge.im.ufrj.br/seminarios-de-probabilidade/