Riemannian Gaussian Distributions on the Space of Symmetric Positive Definite Matrices.
Salem SaidLionel BombrunYannick BerthoumieuJonathan H. MantonPublished in: IEEE Trans. Inf. Theory (2017)
Keyphrases
- symmetric positive definite matrices
- gaussian distribution
- covariance matrices
- valued data
- riemannian metric
- dictionary learning
- log euclidean
- vector space
- riemannian manifolds
- matrix valued
- maximum likelihood
- sparse representation
- euclidean space
- covariance matrix
- lie group
- shape space
- vector valued
- finite dimensional
- sparse coding
- expectation maximization
- affine invariant
- order statistics
- gaussian mixture model
- shape analysis
- parameter space
- kl divergence
- similarity search
- em algorithm