Approximating the maximum weighted decomposable graph problem with applications to probabilistic graphical models.
Aritz PérezChristian BlumJosé Antonio LozanoPublished in: PGM (2018)
Keyphrases
- probabilistic graphical models
- markov networks
- graphical models
- first order logic
- belief propagation
- maximum likelihood
- bayesian networks
- exact inference
- probabilistic model
- approximate inference
- latent variables
- maximum margin
- hidden variables
- markov random field
- parameter learning
- special case
- conditional random fields
- neural network
- probabilistic inference
- document classification
- posterior probability
- directed acyclic graph
- soft computing
- machine learning
- knowledge representation
- computational intelligence
- higher order