Learning Probabilistic Decision Graphs

Manfred Jaeger; Jens Dalgaard; Tomi Silander

Learning Probabilistic Decision Graphs

Manfred Jaeger, Jens Dalgaard, Tomi Silander

Institut for Datalogi

Publikation: Bidrag til bog/antologi/rapport/konference proceeding › Konferenceartikel i proceeding › Forskning

475 Downloads (Pure)

Abstract

Probabilistic decision graphs (PDGs) are a representation language for probability distributions based on binary decision diagrams. PDGs can encode (context-specific) independence relations that cannot be captured in a Bayesian network structure, and can sometimes provide computationally more efficient representations than Bayesian networks. In this paper we present an algorithm for learning PDGs from data. First experiments show that the algorithm is capable of learning optimal PDG representations in some cases, and that the computational efficiency of PDG models learned from real-life data is very close to the computational efficiency of Bayesian network models.

Originalsprog	Engelsk
Titel	Proceedings of the Second European Workshop on Probabilistic Graphical Models
Redaktører	Peter Lucas
Publikationsdato	2004
Status	Udgivet - 2004
Begivenhed	PGM´04 - Leiden, Holland Varighed: 4 sep. 2004 → 8 sep. 2004 Konferencens nummer: 2

Konference

Konference	PGM´04
Nummer	2
Land/Område	Holland
By	Leiden
Periode	04/09/2004 → 08/09/2004

Adgang til dokumentet

Pgm04finalForlagets udgivne version, 103 KB

AUB Link

Søg efter materialet i Aalborg Universitetsbiblioteks søgemaskine

Citationsformater

@inproceedings{1c5347109c2e11db8ed6000ea68e967b,

title = "Learning Probabilistic Decision Graphs",

abstract = "Probabilistic decision graphs (PDGs) are a representation language for probability distributions based on binary decision diagrams. PDGs can encode (context-specific) independence relations that cannot be captured in a Bayesian network structure, and can sometimes provide computationally more efficient representations than Bayesian networks. In this paper we present an algorithm for learning PDGs from data. First experiments show that the algorithm is capable of learning optimal PDG representations in some cases, and that the computational efficiency of PDG models learned from real-life data is very close to the computational efficiency of Bayesian network models.",

author = "Manfred Jaeger and Jens Dalgaard and Tomi Silander",

year = "2004",

language = "English",

editor = "Peter Lucas",

booktitle = "Proceedings of the Second European Workshop on Probabilistic Graphical Models",

note = "PGM´04 ; Conference date: 04-09-2004 Through 08-09-2004",

}

TY - GEN

T1 - Learning Probabilistic Decision Graphs

AU - Jaeger, Manfred

AU - Dalgaard, Jens

AU - Silander, Tomi

N1 - Conference code: 2

PY - 2004

Y1 - 2004

N2 - Probabilistic decision graphs (PDGs) are a representation language for probability distributions based on binary decision diagrams. PDGs can encode (context-specific) independence relations that cannot be captured in a Bayesian network structure, and can sometimes provide computationally more efficient representations than Bayesian networks. In this paper we present an algorithm for learning PDGs from data. First experiments show that the algorithm is capable of learning optimal PDG representations in some cases, and that the computational efficiency of PDG models learned from real-life data is very close to the computational efficiency of Bayesian network models.

AB - Probabilistic decision graphs (PDGs) are a representation language for probability distributions based on binary decision diagrams. PDGs can encode (context-specific) independence relations that cannot be captured in a Bayesian network structure, and can sometimes provide computationally more efficient representations than Bayesian networks. In this paper we present an algorithm for learning PDGs from data. First experiments show that the algorithm is capable of learning optimal PDG representations in some cases, and that the computational efficiency of PDG models learned from real-life data is very close to the computational efficiency of Bayesian network models.

M3 - Article in proceeding

BT - Proceedings of the Second European Workshop on Probabilistic Graphical Models

A2 - Lucas, Peter

T2 - PGM´04

Y2 - 4 September 2004 through 8 September 2004

ER -

Learning Probabilistic Decision Graphs

Abstract

Konference

Adgang til dokumentet

AUB Link

Fingeraftryk

Citationsformater