Equivalences between maximum a posteriori inference in Bayesian networks and maximum expected utility computation in influence diagrams

DOI10.1016/J.IJAR.2015.03.007MaRDI QIDQ895536zbMATH OpenOpenAlexWikidataFDO

Authors D. D. Maua

Publication date 3 December 2015

Published in International Journal of Approximate Reasoning (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.ijar.2015.03.007

zbMATH Keywords

computational complexityBayesian networksinfluence diagramsmaximum expected utilitymaximum a posteriori inference

Mathematics Subject Classification ID

Multivariate analysis (62H99) Reasoning under uncertainty in the context of artificial intelligence (68T37) Computational difficulty of problems (lower bounds, completeness, difficulty of approximation, etc.) (68Q17)

Recommendations

• Equivalences between maximum a posteriori inference in Bayesian networks and maximum expected utility computation in influence diagrams
• scientific article; zbMATH DE number 2243356
• Approximating MAPs for belief networks is NP-hard and other theorems
• Most probable explanations in Bayesian networks: complexity and tractability
• The complexity of approximating MAPs for belief networks with bounded probabilities

Cites work

• scientific article; zbMATH DE number 48344 (Why is no real title available?)
• scientific article; zbMATH DE number 2243356 (Why is no real title available?)
• 2U: an exact interval propagation algorithm for polytrees with binary variables
• A Linear-Time Algorithm for Finding Tree-Decompositions of Small Treewidth
• A computational theory of decision networks
• Bayesian Networks and Decision Graphs
• Binary join trees for computing marginals in the Shenoy-Shafer architecture
• Credal networks
• Introduction to imprecise probabilities
• Mini-buckets: a general scheme for bounded inference
• On the complexity of solving polytree-shaped limited memory influence diagrams with binary variables
• Probabilistic graphical models
• Probabilistic graphical models.
• Probabilistic inference in credal networks: new complexity results
• Representing and solving decision problems with limited information
• Risk, ambiguity and the Savage axioms
• Sequential decision making with partially ordered preferences
• Solving limited memory influence diagrams
• Speeding up \(k\)-neighborhood local search in limited memory influence diagrams
• The necessity of bounded treewidth for efficient inference in Bayesian networks
• Updating credal networks is approximable in polynomial time

Cited in

(2)

• Equivalences between maximum a posteriori inference in Bayesian networks and maximum expected utility computation in influence diagrams
• An integrated approach to solving influence diagrams and finite-horizon partially observable decision processes

Describes a project that uses

Uses Software

• k-Neighborhood

This page was built for publication: Equivalences between maximum a posteriori inference in Bayesian networks and maximum expected utility computation in influence diagrams

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q895536)