Inference in credal networks through integer programming

Cassio Polpo de Campos; Fabio Gagliardi Cozman

Inference in credal networks through integer programming

Cassio Polpo de Campos, Fabio Gagliardi Cozman

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

Abstract

A credal network associates a directed acyclic graph with a collection of sets of probability measures; it offers a compact representation for sets of multivariate distributions. In this paper we present a new algorithm for inference in credal networks based on an integer programming reformulation. We are concerned with computation of lower/upper probabilities for a variable in a given credal network. Experiments reported in this paper indicate that this new algorithm has better performance than existing ones for some important classes of networks.

Original language	English
Title of host publication	ISIPTA 2007 - Proceedings of the 5th International Symposium on Imprecise Probability
Subtitle of host publication	Theories and Applications
Publisher	Society for Imprecise Probability: Theories and Applications
Pages	145-154
Number of pages	10
ISBN (Print)	9788086742205
Publication status	Published - 1 Dec 2007
Externally published	Yes
Event	5th International Symposium on Imprecise Probability: Theories and Applications, ISIPTA 2007 - Prague, Czech Republic Duration: 16 Jul 2007 → 19 Jul 2007

Conference

Conference	5th International Symposium on Imprecise Probability: Theories and Applications, ISIPTA 2007
Country/Territory	Czech Republic
City	Prague
Period	16/07/07 → 19/07/07

Bibliographical note

(oral presentation, blind peer reviewed by >3 reviewers)

Keywords

Credal networks
Integer programming

Cite this

@inproceedings{0ec2c380b9664b1baff5b4ae75a776db,

title = "Inference in credal networks through integer programming",

abstract = "A credal network associates a directed acyclic graph with a collection of sets of probability measures; it offers a compact representation for sets of multivariate distributions. In this paper we present a new algorithm for inference in credal networks based on an integer programming reformulation. We are concerned with computation of lower/upper probabilities for a variable in a given credal network. Experiments reported in this paper indicate that this new algorithm has better performance than existing ones for some important classes of networks.",

keywords = "Credal networks, Integer programming",

author = "{de Campos}, {Cassio Polpo} and Cozman, {Fabio Gagliardi}",

note = "(oral presentation, blind peer reviewed by >3 reviewers); 5th International Symposium on Imprecise Probability: Theories and Applications, ISIPTA 2007 ; Conference date: 16-07-2007 Through 19-07-2007",

year = "2007",

month = dec,

day = "1",

language = "English",

isbn = "9788086742205",

pages = "145--154",

booktitle = "ISIPTA 2007 - Proceedings of the 5th International Symposium on Imprecise Probability",

publisher = "Society for Imprecise Probability: Theories and Applications",

}

de Campos, CP & Cozman, FG 2007, Inference in credal networks through integer programming. in ISIPTA 2007 - Proceedings of the 5th International Symposium on Imprecise Probability: Theories and Applications. Society for Imprecise Probability: Theories and Applications, pp. 145-154, 5th International Symposium on Imprecise Probability: Theories and Applications, ISIPTA 2007, Prague, Czech Republic, 16/07/07.

Inference in credal networks through integer programming. / de Campos, Cassio Polpo; Cozman, Fabio Gagliardi.
ISIPTA 2007 - Proceedings of the 5th International Symposium on Imprecise Probability: Theories and Applications. Society for Imprecise Probability: Theories and Applications, 2007. p. 145-154.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Inference in credal networks through integer programming

AU - de Campos, Cassio Polpo

AU - Cozman, Fabio Gagliardi

N1 - (oral presentation, blind peer reviewed by >3 reviewers)

PY - 2007/12/1

Y1 - 2007/12/1

N2 - A credal network associates a directed acyclic graph with a collection of sets of probability measures; it offers a compact representation for sets of multivariate distributions. In this paper we present a new algorithm for inference in credal networks based on an integer programming reformulation. We are concerned with computation of lower/upper probabilities for a variable in a given credal network. Experiments reported in this paper indicate that this new algorithm has better performance than existing ones for some important classes of networks.

AB - A credal network associates a directed acyclic graph with a collection of sets of probability measures; it offers a compact representation for sets of multivariate distributions. In this paper we present a new algorithm for inference in credal networks based on an integer programming reformulation. We are concerned with computation of lower/upper probabilities for a variable in a given credal network. Experiments reported in this paper indicate that this new algorithm has better performance than existing ones for some important classes of networks.

KW - Credal networks

KW - Integer programming

UR - http://www.scopus.com/inward/record.url?scp=84883251810&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9788086742205

SP - 145

EP - 154

BT - ISIPTA 2007 - Proceedings of the 5th International Symposium on Imprecise Probability

PB - Society for Imprecise Probability: Theories and Applications

T2 - 5th International Symposium on Imprecise Probability: Theories and Applications, ISIPTA 2007

Y2 - 16 July 2007 through 19 July 2007

ER -

Inference in credal networks through integer programming

Abstract

Conference

Bibliographical note

Keywords

Other files and links

Fingerprint

Cite this