Randomly initialized EM algorithm for two-component Gaussian mixture achieves near optimality in O(√n) iterations.
Yihong WuHarrison H. ZhouPublished in: CoRR (2019)
Keyphrases
- gaussian mixture
- em algorithm
- expectation maximization
- mixture model
- maximum likelihood
- optimal solution
- gaussian mixture model
- parameter estimation
- generative model
- maximum likelihood estimation
- probability density
- expectation maximisation
- density estimation
- maximum a posteriori
- probability density function
- log likelihood
- unsupervised learning
- image processing
- closed form
- knowledge discovery
- information theoretic
- k means