Skip to main content
SpringerLink
Log in

Equivalences between Maximum a Posteriori Inference in Bayesian Networks and Maximum Expected Utility Computation in Influence Diagrams

  • Conference paper
Book cover Probabilistic Graphical Models (PGM 2014)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 8754))

Included in the following conference series:

  • 2064 Accesses

Abstract

Two important tasks in probabilistic reasoning are the computation of the maximum posterior probability of a given subset of the variables in a Bayesian network (MAP), and the computation of the maximum expected utility of a strategy in an influence diagram (MEU). Despite their similarities, research on both problems have largely been conducted independently, with algorithmic solutions and insights designed for one problem not (trivially) transferable to the other one. In this work, we show constructively that these two problems are equivalent in the sense that any algorithm designed for one problem can be used to solve the other with small overhead. These equivalences extend the toolbox of either problem, and shall foster new insights into their solution.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Antonucci, A., Piatti, A.: Modeling unreliable observations in Bayesian networks by credal networks. In: Godo, L., Pugliese, A. (eds.) SUM 2009. LNCS, vol. 5785, pp. 28–39. Springer, Heidelberg (2009)

    Chapter  Google Scholar 

  2. Bodlaender, H., Koster, A., van den Eijkhof, F., van der Gaag, L.: Pre-processing for triangulation of probabilistic networks. In: Proceedings of the 17th Conference on Uncertainty in Artificial Intelligence (UAI), pp. 32–39 (2001)

    Google Scholar 

  3. de Campos, C.P.: New complexity results for MAP in Bayesian networks. In: Proceedings of the 22nd International Joint Conference on Artificial Intelligence (IJCAI), pp. 2100–2106 (2011)

    Google Scholar 

  4. de Campos, L.M., Gámez, J.A., Moral, S.: Partial abductive inference in Bayesian networks by using probability trees. In: 5th International Conference on Enterprise Information Systems (ICEIS), pp. 83–91 (2003)

    Google Scholar 

  5. de Campos, C.P., Ji, Q.: Strategy selection in influence diagrams using imprecise probabilities. In: Proceedings of the 24th Conference in Uncertainty in Artificial Intelligence (UAI), pp. 121–128 (2008)

    Google Scholar 

  6. de Paz, R.C., Gómez-Olmedo, M., Cano, A.: Approximate inference in influence diagrams using binary trees. In: Proceedings of the 6th European Workshop on Probabilistic Graphical Models (PGM), pp. 43–50 (2012)

    Google Scholar 

  7. Dechter, R.: An anytime approximation for optimizing policies under uncertainty. In: Workshop of Decision Theoretic Planning, AIPS (2000)

    Google Scholar 

  8. Dechter, R., Rish, I.: Mini-buckets: A general scheme for bounded inference. Journal of the ACM 50(2), 107–153 (2003)

    Article  MathSciNet  Google Scholar 

  9. Detwarasiti, A., Shachter, R.D.: Influence diagrams for team decision analysis. Decision Analysis 2(4), 207–228 (2005)

    Article  Google Scholar 

  10. Howard, R.A., Matheson, J.E.: Influence diagrams. In: Readings on the Principles and Applications of Decision Analysis, pp. 721–762. Strategic Decisions Group (1984)

    Google Scholar 

  11. Huang, J., Chavira, M., Darwiche, A.: Solving MAP exactly by searching on compiled arithmetic circuits. In: Proceedings of the 21st National Conference on Artificial Intelligence (NCAI), pp. 1143–1148 (2006)

    Google Scholar 

  12. Jensen, F.V., Nielsen, T.D.: Bayesian Networks and Decision Graphs, 2nd edn. Information Science and Statistics. Springer (2007)

    Google Scholar 

  13. Jiang, J., Rai, P., Daume III, H.: Message-passing for approximate MAP inference with latent variables. In: Advances in Neural Information Processing Systems 24 (NIPS), pp. 1197–1205 (2011)

    Google Scholar 

  14. Khaled, A., Yuan, C., Hansen, E.: Solving limited memory influence diagrams using branch-and-bound search. In: Proceedings of the 29th Conference on Uncertainty in Artificial Intelligence, UAI (2013)

    Google Scholar 

  15. Koller, D., Friedman, N.: Probabilistic Graphical Models. MIT Press (2009)

    Google Scholar 

  16. Lauritzen, S.L., Nilsson, D.: Representing and solving decision problems with limited information. Management Science 47, 1235–1251 (2001)

    Article  MATH  Google Scholar 

  17. Lim, H., Yuan, C., Hansen, E.: Scaling up MAP search in Bayesian networks using external memory. In: Proceedings of the 5th European Workshop on Probabilistic Graphical Models (PGM), pp. 177–184 (2010)

    Google Scholar 

  18. Liu, Q., Ihler, A.: Variational algorithms for marginal MAP. In: Proceedings of the 27th Conference on Uncertainty in Artificial Intelligence (UAI), pp. 453–462 (2011)

    Google Scholar 

  19. Liu, Q., Ihler, A.: Belief propagation for structured decision making. In: Proceedings of the 28th Conference on Uncertainty in Artificial Intelligence (UAI), pp. 523–532 (2012)

    Google Scholar 

  20. Madsen, A.L., Nilsson, D.: Solving influence diagrams using HUGIN, Shafer-Shenoy and lazy propagation. In: Proceedings of the 17th Conference in Uncertainty in Artificial Intelligence (UAI), pp. 337–345 (2001)

    Google Scholar 

  21. Mauá, D.D., de Campos, C.P.: Anytime marginal MAP inference. In: Proceedings of the 28th International Conference on Machine Learning (ICML), pp. 1471–1478 (2012)

    Google Scholar 

  22. Mauá, D.D., de Campos, C.P., Zaffalon, M.: The complexity of approximately solving influence diagrams. In: Proceedings of the 28th Conference on Uncertainty in Artificial Intelligence (UAI), pp. 604–613 (2012)

    Google Scholar 

  23. Mauá, D.D., de Campos, C.P., Zaffalon, M.: On the complexity of solving polytree-shaped limited memory influence diagrams with binary variables. Artificial Intelligence 205, 30–38 (2013)

    Article  MathSciNet  Google Scholar 

  24. Mauá, D.D., de Campos, C.P.: Solving decision problems with limited information. In: Advances in Neural Information Processing Systems 24 (NIPS), pp. 603–611 (2011)

    Google Scholar 

  25. Mauá, D.D., de Campos, C.P., Zaffalon, M.: Solving limited memory influence diagrams. Journal of Artificial Intelligence Research 44, 97–140 (2012)

    MathSciNet  MATH  Google Scholar 

  26. Meek, C., Wexler, Y.: Approximating max-sum-product problems using multiplicative error bounds. Bayesian Statistics 9, 439–472 (2011)

    MathSciNet  Google Scholar 

  27. Nilsson, D., Höhle, M.: Computing bounds on expected utilities for optimal policies based on limited information. Research Report 94, Dina (2001)

    Google Scholar 

  28. Nilsson, D., Lauritzen, S.L.: Evaluating influence diagrams using LIMIDs. In: Proceedings of the 16th Conference in Uncertainty in Artificial Intelligence (UAI), pp. 436–445 (2000)

    Google Scholar 

  29. Park, J.D., Darwiche, A.: Solving MAP exactly using systematic search. In: Proceedings of the 19th Conference on Uncertainty in Artificial Intelligence (UAI), pp. 459–468 (2003)

    Google Scholar 

  30. Park, J.D., Darwiche, A.: Complexity results and approximation strategies for MAP explanations. Journal of Artificial Intelligence Research 21, 101–133 (2004)

    MathSciNet  MATH  Google Scholar 

  31. Shenoy, P.P.: Binary join trees for computing marginals in the Shenoy-Shafer architecture. International Journal of Approximate Reasoning 17(2-3), 239–263 (1997)

    Article  MathSciNet  MATH  Google Scholar 

  32. Yuan, C., Wu, X., Hansen, E.A.: Solving multistage influence diagrams using branch-and-bound search. In: Proceedings of the 26th Conference on Uncertainty in Artificial Intelligence (UAI), pp. 691–700 (2010)

    Google Scholar 

  33. Zhang, N.L., Qi, R., Poole, D.: A computational theory of decision networks. International Journal of Approximate Reasoning 11(2), 83–158 (1994)

    Article  MathSciNet  MATH  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Universidade de São Paulo, São Paulo, Brazil

    Denis D. Mauá

Authors
  1. Denis D. Mauá
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Utrecht University, Faculty of Science, Department of Information and Computing Sciences, Princetonplein 5, 3584 CC Utrecht, The Netherlands

    Linda C. van der Gaag

  2. Utrecht University, Faculty of Science, Department of Information and Computing Sciences, Princetonplein 5, 3584 CC Utrecht,, The Netherlands

    Ad J. Feelders

Rights and permissions

Reprints and permissions

Copyright information

© 2014 Springer International Publishing Switzerland

About this paper

Cite this paper

Mauá, D.D. (2014). Equivalences between Maximum a Posteriori Inference in Bayesian Networks and Maximum Expected Utility Computation in Influence Diagrams. In: van der Gaag, L.C., Feelders, A.J. (eds) Probabilistic Graphical Models. PGM 2014. Lecture Notes in Computer Science(), vol 8754. Springer, Cham. https://doi.org/10.1007/978-3-319-11433-0_21

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-11433-0_21

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-11432-3

  • Online ISBN: 978-3-319-11433-0

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation