Delta-AI: Local objectives for amortized inference in sparse graphical models.
Jean-Pierre FaletHae Beom LeeNikolay MalkinChen SunDragos SecrieruDinghuai ZhangGuillaume LajoieYoshua BengioPublished in: CoRR (2023)
Keyphrases
- graphical models
- probabilistic inference
- exact inference
- gaussian graphical models
- map inference
- belief networks
- belief propagation
- factor graphs
- bayesian networks
- loopy belief propagation
- undirected graphical models
- probabilistic model
- approximate inference
- efficient inference algorithms
- nonparametric belief propagation
- probabilistic graphical models
- statistical inference
- random variables
- directed graphical models
- directed acyclic
- graphical structure
- conditional random fields
- relational dependency networks
- probabilistic networks
- markov networks
- structure learning
- possibilistic networks
- collective classification
- conditional independence
- knowledge representation
- statistical relational learning
- machine learning
- message passing
- exponential family
- markov logic networks
- worst case
- marginal probabilities
- bayesian inference
- chain graphs
- probabilistic reasoning
- markov chain monte carlo
- generative model
- dynamic bayesian networks
- partition function
- search algorithm
- posterior probability
- inference process