Weighing and Integrating Evidence for Stochastic Simulation in Bayesian Networks

By R. Fung, Kuo-Chu Chang. Conference on Uncertainty in Artificial Intelligence, 2013

328 citations recorded by the source corpus.

Abstract Stochastic simulation approaches perform probabilistic inference in Bayesian networks by estimating the probability of an event based on the frequency that the event occurs in a set of simulation trials. This paper describes the evidence weighting mechanism, for augmenting the logic sampling stochastic simulation algorithm [Henrion, 1986]. Evidence weighting modifies the logic sampling algorithm by weighting each simulation trial by the likelihood of a network's evidence given the sampled state node values for that trial. We also describe an enhancement to the basic algorithm which uses the evidential integration technique [Chin and Cooper, 1987]. A comparison of the basic evidence weighting mechanism with the Markov blanket algorithm [Pearl, 1987], the logic sampling algorithm, and the evidence integration algorithm is presented. The comparison is aided by analyzing the performance of the algorithms in a simple example network.

Subfields: Artificial Intelligence, Management Science and Operations Research, Software

View Paper: https://www.semanticscholar.org/paper/9e475eff11c29f0d532f18a0710bfd87010ef44d

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Stuart J. Russell
2. Eric Horvitz
3. Michael I. Jordan
4. Gregory F. Cooper
5. David E. Heckerman
6. Harold P. Lehmann
7. Blackford Middleton
8. Max Henrion

In Management Science and Operations Research

1. David E. Heckerman
2. Gregory F. Cooper
3. Qiang Shen
4. Stuart J. Russell
5. Eric Horvitz
6. Michael I. Jordan
7. Kevin B. Korb
8. Ann E. Nicholson

In Software

1. Qiang Shen
2. Stuart J. Russell
3. Eric Horvitz
4. Michael I. Jordan
5. Kevin B. Korb
6. Ann E. Nicholson
7. Stuart Aitken
8. Brian Milch

Citations in the corpus

• Learning Bayesian Network Model Structure from Data (2003, background): “Approximate ones (Henrion, 1988; Fung and Chang, 1989; Schachter and Peot, 1989) are sample-based, and generate an artificial database of samples during the process of estimation (the generated samples are discarded immediately and only the count of those than matched the query is kept).”
• Probabilistic Diagnosis Using a Reformulation of the INTERNIST-1/QMR Knowledge Base (1991, methodology): “This algorithm has been described previously by Fung and Chang [36] and Shachter and Peot [37].”
• Bayesian Artificial Intelligence (2004, methodology): “The logic sampling method was developed by Henrion [106], while likelihood weighting was developed in [87, 248].”
• Probabilistic models with unknown objects (2006, methodology): “There is a simple and elegant way to apply importance sampling to a BN, called likelihood weighting [Fung and Chang, 1990; Shachter and Peot, 1990].”
• Pattern Recognition and Machine Learning (2006, unknown): “An improvement on this approach is called likelihood weighted sampling (Fung and Chang, 1990; Shachter and Peot, 1990) and is based on ancestral sampling of the variables.”
• Learning Bayesian networks: approaches and issues (2011, methodology): “Geiger and Heckerman (1994) use this to learn using continuous data. Taking away the normal assumption, Hofmann and Tresp (1996) use kernel density estimators to model the conditional distribution.”