TY - GEN
T1 - The minimal representation of a system with interacting units using Boltzmann machines
AU - Valle, Mauricio A.
AU - Urbina, Felipe
N1 - Publisher Copyright:
© 2022 ACM.
PY - 2022/10/27
Y1 - 2022/10/27
N2 - 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.
AB - 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.
KW - Boltzmann machine
KW - Coupling network
KW - critical network
KW - Kullback-Leibler.
KW - maximum entropy principle
UR - http://www.scopus.com/inward/record.url?scp=85148472530&partnerID=8YFLogxK
U2 - 10.1145/3571697.3571710
DO - 10.1145/3571697.3571710
M3 - Contribución a la conferencia
AN - SCOPUS:85148472530
T3 - ACM International Conference Proceeding Series
SP - 98
EP - 103
BT - ESSE 2022 - 2022 3rd European Symposium on Software Engineering
PB - Association for Computing Machinery
T2 - 3rd European Symposium on Software Engineering, ESSE 2022
Y2 - 27 October 2022 through 29 October 2022
ER -