Importance sampling-based estimation over AND/OR search spaces for graphical models

DOI10.1016/j.artint.2012.03.001zbMath1251.68241MaRDI QIDQ1761277

Vibhav Gogate, Rina Dechter

Publication date: 15 November 2012

Published in: Artificial Intelligence (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.artint.2012.03.001

zbMATH Keywords

Bayesian networks; importance sampling; variance reduction; constraint networks; probabilistic inference; graphical models; approximate inference; model counting; Markov networks

Mathematics Subject Classification ID

68T37: Reasoning under uncertainty in the context of artificial intelligence

68T20: Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.)

Related Items

Advanced SMT techniques for weighted model integration

Uses Software

• AIS-BN

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• SampleSearch: importance sampling in presence of determinism
• Arc refractor methods for adaptive importance sampling on large Bayesian networks under evidential reasoning
• AND/OR search spaces for graphical models
• A modified simulation scheme for inference in Bayesian networks
• The properties of the cross-match estimate and split sampling
• Dynamic importance sampling in Bayesian networks based on probability trees
• On probabilistic inference by weighted model counting
• Importance sampling algorithms for Bayesian networks: principles and performance
• The computational complexity of probabilistic inference using Bayesian belief networks
• On the Exact Variance of Products
• A differential approach to inference in Bayesian networks
• Constructing Free-Energy Approximations and Generalized Belief Propagation Algorithms
• Join-Graph Propagation Algorithms
• Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images
• Bayesian Inference in Econometric Models Using Monte Carlo Integration
• Monte Carlo strategies in scientific computing
• Recursive conditioning
• A general scheme for automatic generation of search heuristics from specification \(dependencies^{*}\)