Efficient learning of decomposable models with a bounded clique size

The learning of probability distributions from data is a ubiquitous problem in the fields of Statistics and Artificial Intelligence. During the last decades several learning algorithms have been proposed to learn probability distributions based on decomposable models due to their advantageous theore...

Descripción completa

Detalles Bibliográficos
Autores: Pérez Martínez, Aritz, Inza Cano, Iñaki, Lozano Alonso, José Antonio
Tipo de recurso: informe técnico
Fecha de publicación:2014
País:España
Institución:Universidad del País Vasco
Repositorio:Addi. Archivo Digital para la Docencia y la Investigación
OAI Identifier:oai:addi.ehu.eus:10810/12361
Acceso en línea:http://hdl.handle.net/10810/12361
Access Level:acceso abierto
Palabra clave:approximating probability distributions
decomposable models
bounded clique size
maximum likelihood problem
efficient algorithms
Chow and Liu's algorithm
id ES_561e2bc16f9cc2b7e57aba1460e6643f
oai_identifier_str oai:addi.ehu.eus:10810/12361
network_acronym_str ES
network_name_str España
repository_id_str
spelling Efficient learning of decomposable models with a bounded clique sizePérez Martínez, AritzInza Cano, IñakiLozano Alonso, José Antonioapproximating probability distributionsdecomposable modelsbounded clique sizemaximum likelihood problemefficient algorithmsChow and Liu's algorithmThe learning of probability distributions from data is a ubiquitous problem in the fields of Statistics and Artificial Intelligence. During the last decades several learning algorithms have been proposed to learn probability distributions based on decomposable models due to their advantageous theoretical properties. Some of these algorithms can be used to search for a maximum likelihood decomposable model with a given maximum clique size, k, which controls the complexity of the model. Unfortunately, the problem of learning a maximum likelihood decomposable model given a maximum clique size is NP-hard for k > 2. In this work, we propose a family of algorithms which approximates this problem with a computational complexity of O(k · n^2 log n) in the worst case, where n is the number of implied random variables. The structures of the decomposable models that solve the maximum likelihood problem are called maximal k-order decomposable graphs. Our proposals, called fractal trees, construct a sequence of maximal i-order decomposable graphs, for i = 2, ..., k, in k − 1 steps. At each step, the algorithms follow a divide-and-conquer strategy based on the particular features of this type of structures. Additionally, we propose a prune-and-graft procedure which transforms a maximal k-order decomposable graph into another one, increasing its likelihood. We have implemented two particular fractal tree algorithms called parallel fractal tree and sequential fractal tree. These algorithms can be considered a natural extension of Chow and Liu’s algorithm, from k = 2 to arbitrary values of k. Both algorithms have been compared against other efficient approaches in artificial and real domains, and they have shown a competitive behavior to deal with the maximum likelihood problem. Due to their low computational complexity they are especially recommended to deal with high dimensional domains.201420142014info:eu-repo/semantics/reportapplication/pdfhttp://hdl.handle.net/10810/12361reponame:Addi. Archivo Digital para la Docencia y la Investigacióninstname:Universidad del País VascoInglésEHU-KZAA-TR;2014-07info:eu-repo/semantics/openAccessoai:addi.ehu.eus:10810/123612026-06-18T09:23:17Z
dc.title.none.fl_str_mv Efficient learning of decomposable models with a bounded clique size
title Efficient learning of decomposable models with a bounded clique size
spellingShingle Efficient learning of decomposable models with a bounded clique size
Pérez Martínez, Aritz
approximating probability distributions
decomposable models
bounded clique size
maximum likelihood problem
efficient algorithms
Chow and Liu's algorithm
title_short Efficient learning of decomposable models with a bounded clique size
title_full Efficient learning of decomposable models with a bounded clique size
title_fullStr Efficient learning of decomposable models with a bounded clique size
title_full_unstemmed Efficient learning of decomposable models with a bounded clique size
title_sort Efficient learning of decomposable models with a bounded clique size
dc.creator.none.fl_str_mv Pérez Martínez, Aritz
Inza Cano, Iñaki
Lozano Alonso, José Antonio
author Pérez Martínez, Aritz
author_facet Pérez Martínez, Aritz
Inza Cano, Iñaki
Lozano Alonso, José Antonio
author_role author
author2 Inza Cano, Iñaki
Lozano Alonso, José Antonio
author2_role author
author
dc.subject.none.fl_str_mv approximating probability distributions
decomposable models
bounded clique size
maximum likelihood problem
efficient algorithms
Chow and Liu's algorithm
topic approximating probability distributions
decomposable models
bounded clique size
maximum likelihood problem
efficient algorithms
Chow and Liu's algorithm
description The learning of probability distributions from data is a ubiquitous problem in the fields of Statistics and Artificial Intelligence. During the last decades several learning algorithms have been proposed to learn probability distributions based on decomposable models due to their advantageous theoretical properties. Some of these algorithms can be used to search for a maximum likelihood decomposable model with a given maximum clique size, k, which controls the complexity of the model. Unfortunately, the problem of learning a maximum likelihood decomposable model given a maximum clique size is NP-hard for k > 2. In this work, we propose a family of algorithms which approximates this problem with a computational complexity of O(k · n^2 log n) in the worst case, where n is the number of implied random variables. The structures of the decomposable models that solve the maximum likelihood problem are called maximal k-order decomposable graphs. Our proposals, called fractal trees, construct a sequence of maximal i-order decomposable graphs, for i = 2, ..., k, in k − 1 steps. At each step, the algorithms follow a divide-and-conquer strategy based on the particular features of this type of structures. Additionally, we propose a prune-and-graft procedure which transforms a maximal k-order decomposable graph into another one, increasing its likelihood. We have implemented two particular fractal tree algorithms called parallel fractal tree and sequential fractal tree. These algorithms can be considered a natural extension of Chow and Liu’s algorithm, from k = 2 to arbitrary values of k. Both algorithms have been compared against other efficient approaches in artificial and real domains, and they have shown a competitive behavior to deal with the maximum likelihood problem. Due to their low computational complexity they are especially recommended to deal with high dimensional domains.
publishDate 2014
dc.date.none.fl_str_mv 2014
2014
2014
dc.type.none.fl_str_mv info:eu-repo/semantics/report
format report
dc.identifier.none.fl_str_mv http://hdl.handle.net/10810/12361
url http://hdl.handle.net/10810/12361
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv EHU-KZAA-TR;2014-07
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:Addi. Archivo Digital para la Docencia y la Investigación
instname:Universidad del País Vasco
instname_str Universidad del País Vasco
reponame_str Addi. Archivo Digital para la Docencia y la Investigación
collection Addi. Archivo Digital para la Docencia y la Investigación
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869408356897128448
score 15,300719