On the exact maximum likelihood inference of Fisher-Bingham distributions using an adjusted holonomic gradient method.
Alfred KumeTomonari SeiPublished in: Stat. Comput. (2018)
Keyphrases
- gradient method
- maximum likelihood
- log likelihood function
- gaussian distribution
- exponential family
- convergence rate
- optimization methods
- step size
- em algorithm
- negative matrix factorization
- convex formulation
- expectation maximization
- bayesian networks
- likelihood function
- maximum likelihood estimation
- natural gradient learning
- posterior probability
- maximum a posteriori
- convergence speed
- nearest neighbor
- support vector machine
- pairwise
- feature extraction
- machine learning