Global Convergence of the EM Algorithm for Mixtures of Two Component Linear Regression.
Jeongyeol KwonWei QianConstantine CaramanisYudong ChenDamek DavisPublished in: COLT (2019)
Keyphrases
- linear regression
- em algorithm
- global convergence
- expectation maximization
- mixture model
- gaussian mixture
- global optimum
- least squares
- convergence speed
- convergence rate
- optimization methods
- mixture distribution
- generative model
- maximum likelihood
- gaussian mixture model
- parameter estimation
- probabilistic model
- maximum likelihood estimation
- hyperparameters
- expectation maximisation
- mixture components
- log likelihood
- incomplete data
- linear models
- density estimation
- probability density function
- maximum a posteriori
- particle swarm
- evolutionary algorithm
- optimization method
- line search
- bayesian framework
- image segmentation
- differential evolution
- step size
- objective function
- machine learning