Computing Functions of Random Variables via Reproducing Kernel Hilbert Space Representations.
Bernhard SchölkopfKrikamol MuandetKenji FukumizuJonas PetersPublished in: CoRR (2015)
Keyphrases
- random variables
- reproducing kernel hilbert space
- graphical models
- probability distribution
- kernel methods
- loss function
- learning theory
- kernel function
- euclidean space
- latent variables
- bayesian networks
- real valued
- gaussian process
- special case
- distance measure
- input space
- density estimation
- data dependent
- domain adaptation
- kernel matrix
- marginal distributions
- shape analysis
- machine learning
- learning problems
- positive definite