Riemannian Gaussian Distributions on the Space of Positive-Definite Quaternion Matrices.
Salem SaidNicolas Le BihanJonathan H. MantonPublished in: GSI (2017)
Keyphrases
- positive definite
- gaussian distribution
- riemannian metric
- symmetric positive definite
- covariance matrices
- covariance matrix
- fisher information
- geometric structure
- riemannian manifolds
- kernel function
- reproducing kernel hilbert space
- lie group
- maximum likelihood
- diffusion tensor
- symmetric matrices
- gaussian mixture model
- input space
- geodesic distance
- euclidean space
- expectation maximization
- kl divergence
- graph kernels
- sufficient conditions
- low dimensional
- distance measure
- principal component analysis
- support vector