Non-approximate Inference for Collective Graphical Models on Path Graphs via Discrete Difference of Convex Algorithm.
Yasunori AkagiNaoki MarumoHideaki KimTakeshi KurashimaHiroyuki TodaPublished in: NeurIPS (2021)
Keyphrases
- graphical models
- approximate inference
- loopy belief propagation
- factor graphs
- graph structure
- belief propagation
- probabilistic model
- probabilistic inference
- probabilistic graphical models
- conditional random fields
- random variables
- exact inference
- bayesian networks
- markov chain monte carlo
- parameter estimation
- variational methods
- matching algorithm
- expectation maximization
- structure learning
- k means
- gaussian process
- energy function
- markov random field
- np hard
- belief networks
- conditional independence
- latent variables
- regression model
- distributed systems
- dynamic programming
- marginal probabilities