Anytime marginal MAP inference

Denis Deratani Mauá; C.P. de Campos

Anytime marginal MAP inference

Denis Deratani Mauá, C.P. de Campos

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/Congresprocedure › Hoofdstuk › Academic › peer review

Samenvatting

This paper presents a new anytime algorithm for the marginal MAP problem in graphical models of bounded treewidth. We show asymptotic convergence and theoretical error bounds for any fixed step. Experiments show that it compares well to a state-of-the-art systematic search algorithm.

Originele taal-2	Engels
Titel	International Conference on Machine Learning (ICML)
Uitgeverij	Omnipress
Pagina's	1471-1478
Aantal pagina's	8
Status	Gepubliceerd - 2012
Extern gepubliceerd	Ja
Evenement	29th International Conference on Machine Learning (ICML 2012) - Edinburgh, Verenigd Koninkrijk Duur: 26 jun. 2012 → 1 jul. 2012 Congresnummer: 29

Congres

Congres	29th International Conference on Machine Learning (ICML 2012)
Verkorte titel	ICML 2012
Land/Regio	Verenigd Koninkrijk
Stad	Edinburgh
Periode	26/06/12 → 1/07/12

Bibliografische nota

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

Citeer dit

@inbook{981eb3c2e86649f0ae81aae93f1226b6,

title = "Anytime marginal MAP inference",

abstract = "This paper presents a new anytime algorithm for the marginal MAP problem in graphical models of bounded treewidth. We show asymptotic convergence and theoretical error bounds for any fixed step. Experiments show that it compares well to a state-of-the-art systematic search algorithm.",

author = "Mau{\'a}, {Denis Deratani} and {de Campos}, C.P.",

note = "(oral presentation, double-blind peer reviewed by >3 reviewers); 29th International Conference on Machine Learning (ICML 2012), ICML 2012 ; Conference date: 26-06-2012 Through 01-07-2012",

year = "2012",

language = "English",

pages = "1471--1478",

booktitle = "International Conference on Machine Learning (ICML)",

publisher = "Omnipress",

}

TY - CHAP

T1 - Anytime marginal MAP inference

AU - Mauá, Denis Deratani

AU - de Campos, C.P.

N1 - Conference code: 29

PY - 2012

Y1 - 2012

N2 - This paper presents a new anytime algorithm for the marginal MAP problem in graphical models of bounded treewidth. We show asymptotic convergence and theoretical error bounds for any fixed step. Experiments show that it compares well to a state-of-the-art systematic search algorithm.

AB - This paper presents a new anytime algorithm for the marginal MAP problem in graphical models of bounded treewidth. We show asymptotic convergence and theoretical error bounds for any fixed step. Experiments show that it compares well to a state-of-the-art systematic search algorithm.

M3 - Chapter

SP - 1471

EP - 1478

BT - International Conference on Machine Learning (ICML)

PB - Omnipress

T2 - 29th International Conference on Machine Learning (ICML 2012)

Y2 - 26 June 2012 through 1 July 2012

ER -

Anytime marginal MAP inference

Samenvatting

Congres

Bibliografische nota

Vingerafdruk

Citeer dit