The EM Algorithm is Adaptively-Optimal for Unbalanced Symmetric Gaussian Mixtures.
Nir WeinbergerGuy BreslerPublished in: J. Mach. Learn. Res. (2022)
Keyphrases
- em algorithm
- gaussian mixture
- expectation maximization
- maximum likelihood
- closed form
- gaussian mixture model
- generative model
- mixture model
- parameter estimation
- maximum likelihood estimation
- probability density function
- log likelihood
- hyperparameters
- covariance matrix
- probabilistic model
- gibbs sampling
- similarity measure
- mixture of gaussians
- mixture components
- mixture modeling
- expectation maximisation
- density estimation
- statistical model
- text classification
- knowledge discovery
- object recognition