Maximum likelihood estimation for the tensor normal distribution: Algorithm, minimum sample size, and empirical bias and dispersion.
Ameur M. ManceurPierre DutilleulPublished in: J. Comput. Appl. Math. (2013)
Keyphrases
- maximum likelihood estimation
- sample size
- worst case
- learning algorithm
- em algorithm
- expectation maximization
- np hard
- computational complexity
- normal distribution
- k means
- parameter estimation
- probabilistic model
- model selection
- standard deviation
- variance reduction
- machine learning
- energy function
- objective function
- density function
- feature extraction
- statistical hypothesis testing