A Robust and Flexible EM Algorithm for Mixtures of Elliptical Distributions with Missing Data.
Florian MouretAlexandre Hippert-FerrerFrédéric PascalJean-Yves TourneretPublished in: CoRR (2022)
Keyphrases
- missing data
- em algorithm
- incomplete data
- expectation maximization
- mixture model
- mixture distribution
- finite mixture models
- gaussian mixture
- finite mixtures
- missing values
- parameter estimation
- maximum likelihood
- mixture components
- gaussian mixture model
- hyperparameters
- maximum likelihood estimation
- generative model
- probabilistic model
- low rank
- probabilistic principal component analysis
- maximum likelihood estimates
- mixture modeling
- matrix factorization
- normal distribution
- expectation maximisation
- likelihood function
- log likelihood
- bayesian framework
- unsupervised learning
- density estimation
- image segmentation
- graphical models
- probability distribution
- bayesian networks
- probability density function
- low rank matrix
- model selection