Using contrastive divergence to seed Monte Carlo MLE for exponential-family random graph models.
Pavel N. KrivitskyPublished in: Comput. Stat. Data Anal. (2017)
Keyphrases
- monte carlo
- exponential family
- maximum likelihood
- markov chain monte carlo
- em algorithm
- parameter estimation
- markov chain
- closed form
- graphical models
- expectation maximization
- mixture model
- missing values
- particle filter
- maximum a posteriori
- density estimation
- gaussian distribution
- simulated annealing
- image segmentation
- knowledge discovery
- hyperparameters
- hidden variables
- probabilistic model
- variational methods
- prior knowledge