The minimal representation of a system with interacting units using Boltzmann machines

Mauricio A. Valle, Felipe Urbina

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper presents an alternative methodology to find a network model with the least amount of critical bonds necessary to represent the behavior of the interacting elements of a system. The model is based on a network of couplings inferred by an non-restricted Boltzmann machine, which allows finding a maximum entropy distribution (ME). For N elements, the process starts by removing from the set of N(N-1)/2 bonds, those with the lowest intensity and calculating the Kullback-Leibler divergence (KL) in each step. The edge removal process stops before there is a drastic increase in the KL divergence. This process was applied to the European market indices over two different periods. The results provide an interesting description of the most significant interactions driving the market and, at the same time, identify markets with higher system importance.

Original languageEnglish
Title of host publicationESSE 2022 - 2022 3rd European Symposium on Software Engineering
PublisherAssociation for Computing Machinery
Pages98-103
Number of pages6
ISBN (Electronic)9781450397308
DOIs
StatePublished - 27 Oct 2022
Event3rd European Symposium on Software Engineering, ESSE 2022 - Rome, Italy
Duration: 27 Oct 202229 Oct 2022

Publication series

NameACM International Conference Proceeding Series

Conference

Conference3rd European Symposium on Software Engineering, ESSE 2022
Country/TerritoryItaly
CityRome
Period27/10/2229/10/22

Keywords

  • Boltzmann machine
  • Coupling network
  • critical network
  • Kullback-Leibler.
  • maximum entropy principle

Fingerprint

Dive into the research topics of 'The minimal representation of a system with interacting units using Boltzmann machines'. Together they form a unique fingerprint.

Cite this