Lifted Maximum Expected Utility

Marcel Gehrke; Tanya Braun; Ralf Möller; Alexander Waschkau; Christoph Strumann; Jost Steinhäuser

Lifted Maximum Expected Utility

Marcel Gehrke, Tanya Braun, Ralf Möller, Alexander Waschkau, Christoph Strumann, Jost Steinhäuser

Abstract

The lifted junction tree algorithm (LJT) answers multiple queries efficiently for relational models under uncertainties by building and then reusing a first-order cluster representation. We extend the underling model representation of LJT, which is called parameterised probabilistic model, to calculate a lifted solution to the maximum expected utility (MEU) problem. Specifically, this paper contributes (i) action and utility nodes for parameterised probabilistic models, resulting in parameterised probabilistic decision models and (ii) meuLJT, an algorithm to solve the MEU problem using parameterised probabilistic decision models efficiently, while also being able to answer multiple marginal queries.

Original language	English
Title of host publication	Artificial Intelligence in Health
Editors	Fernando Koch, Andrew Koster, David Riaño, Sara Montagna, Michael Schumacher, Annette ten Teije, Christian Guttmann, Manfred Reichert, Isabelle Bichindaritz, Pau Herrero, Richard Lenz, Beatriz López, Cindy Marling, Clare Martin, Stefania Montani, Nirmalie Wiratunga
Number of pages	11
Place of Publication	Cham
Publisher	Springer International Publishing
Publication date	2019
Pages	131-141
ISBN (Print)	978-3-030-12738-1
Publication status	Published - 2019

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Cite this

Gehrke, M., Braun, T., Möller, R., Waschkau, A., Strumann, C., & Steinhäuser, J. (2019). Lifted Maximum Expected Utility. In F. Koch, A. Koster, D. Riaño, S. Montagna, M. Schumacher, A. ten Teije, C. Guttmann, M. Reichert, I. Bichindaritz, P. Herrero, R. Lenz, B. López, C. Marling, C. Martin, S. Montani, & N. Wiratunga (Eds.), Artificial Intelligence in Health (pp. 131-141). Springer International Publishing.

Gehrke, Marcel ; Braun, Tanya ; Möller, Ralf et al. / Lifted Maximum Expected Utility. Artificial Intelligence in Health. editor / Fernando Koch ; Andrew Koster ; David Riaño ; Sara Montagna ; Michael Schumacher ; Annette ten Teije ; Christian Guttmann ; Manfred Reichert ; Isabelle Bichindaritz ; Pau Herrero ; Richard Lenz ; Beatriz López ; Cindy Marling ; Clare Martin ; Stefania Montani ; Nirmalie Wiratunga. Cham : Springer International Publishing, 2019. pp. 131-141

@inproceedings{182167c363c04fdd9b2ab11640e0ff5f,

title = "Lifted Maximum Expected Utility",

abstract = "The lifted junction tree algorithm (LJT) answers multiple queries efficiently for relational models under uncertainties by building and then reusing a first-order cluster representation. We extend the underling model representation of LJT, which is called parameterised probabilistic model, to calculate a lifted solution to the maximum expected utility (MEU) problem. Specifically, this paper contributes (i) action and utility nodes for parameterised probabilistic models, resulting in parameterised probabilistic decision models and (ii) meuLJT, an algorithm to solve the MEU problem using parameterised probabilistic decision models efficiently, while also being able to answer multiple marginal queries.",

author = "Marcel Gehrke and Tanya Braun and Ralf M{\"o}ller and Alexander Waschkau and Christoph Strumann and Jost Steinh{\"a}user",

year = "2019",

language = "English",

isbn = "978-3-030-12738-1",

pages = "131--141",

editor = "Fernando Koch and Andrew Koster and David Ria{\~n}o and Sara Montagna and Michael Schumacher and {ten Teije}, Annette and Christian Guttmann and Manfred Reichert and Isabelle Bichindaritz and Pau Herrero and Richard Lenz and Beatriz L{\'o}pez and Cindy Marling and Clare Martin and Stefania Montani and Nirmalie Wiratunga",

booktitle = "Artificial Intelligence in Health",

publisher = "Springer International Publishing",

}

Gehrke, M, Braun, T, Möller, R, Waschkau, A, Strumann, C & Steinhäuser, J 2019, Lifted Maximum Expected Utility. in F Koch, A Koster, D Riaño, S Montagna, M Schumacher, A ten Teije, C Guttmann, M Reichert, I Bichindaritz, P Herrero, R Lenz, B López, C Marling, C Martin, S Montani & N Wiratunga (eds), Artificial Intelligence in Health. Springer International Publishing, Cham, pp. 131-141.

Lifted Maximum Expected Utility. / Gehrke, Marcel; Braun, Tanya; Möller, Ralf et al.
Artificial Intelligence in Health. ed. / Fernando Koch; Andrew Koster; David Riaño; Sara Montagna; Michael Schumacher; Annette ten Teije; Christian Guttmann; Manfred Reichert; Isabelle Bichindaritz; Pau Herrero; Richard Lenz; Beatriz López; Cindy Marling; Clare Martin; Stefania Montani; Nirmalie Wiratunga. Cham: Springer International Publishing, 2019. p. 131-141.

Research output: Chapters in Books/Reports/Conference Proceedings › Conference contribution › peer-review

TY - GEN

T1 - Lifted Maximum Expected Utility

AU - Gehrke, Marcel

AU - Braun, Tanya

AU - Möller, Ralf

AU - Waschkau, Alexander

AU - Strumann, Christoph

AU - Steinhäuser, Jost

PY - 2019

Y1 - 2019

N2 - The lifted junction tree algorithm (LJT) answers multiple queries efficiently for relational models under uncertainties by building and then reusing a first-order cluster representation. We extend the underling model representation of LJT, which is called parameterised probabilistic model, to calculate a lifted solution to the maximum expected utility (MEU) problem. Specifically, this paper contributes (i) action and utility nodes for parameterised probabilistic models, resulting in parameterised probabilistic decision models and (ii) meuLJT, an algorithm to solve the MEU problem using parameterised probabilistic decision models efficiently, while also being able to answer multiple marginal queries.

AB - The lifted junction tree algorithm (LJT) answers multiple queries efficiently for relational models under uncertainties by building and then reusing a first-order cluster representation. We extend the underling model representation of LJT, which is called parameterised probabilistic model, to calculate a lifted solution to the maximum expected utility (MEU) problem. Specifically, this paper contributes (i) action and utility nodes for parameterised probabilistic models, resulting in parameterised probabilistic decision models and (ii) meuLJT, an algorithm to solve the MEU problem using parameterised probabilistic decision models efficiently, while also being able to answer multiple marginal queries.

M3 - Conference contribution

SN - 978-3-030-12738-1

SP - 131

EP - 141

BT - Artificial Intelligence in Health

A2 - Koch, Fernando

A2 - Koster, Andrew

A2 - Riaño, David

A2 - Montagna, Sara

A2 - Schumacher, Michael

A2 - ten Teije, Annette

A2 - Guttmann, Christian

A2 - Reichert, Manfred

A2 - Bichindaritz, Isabelle

A2 - Herrero, Pau

A2 - Lenz, Richard

A2 - López, Beatriz

A2 - Marling, Cindy

A2 - Martin, Clare

A2 - Montani, Stefania

A2 - Wiratunga, Nirmalie

PB - Springer International Publishing

CY - Cham

ER -

Gehrke M, Braun T, Möller R, Waschkau A, Strumann C , Steinhäuser J. Lifted Maximum Expected Utility. In Koch F, Koster A, Riaño D, Montagna S, Schumacher M, ten Teije A, Guttmann C, Reichert M, Bichindaritz I, Herrero P, Lenz R, López B, Marling C, Martin C, Montani S, Wiratunga N, editors, Artificial Intelligence in Health. Cham: Springer International Publishing. 2019. p. 131-141

Lifted Maximum Expected Utility

Abstract

UN SDGs

Fingerprint

Cite this