High-dimensional regression with gaussian mixtures and partially-latent response variables.
Antoine DeleforgeFlorence ForbesRadu HoraudPublished in: Stat. Comput. (2015)
Keyphrases
- gaussian mixture
- high dimensional
- variable selection
- em algorithm
- gaussian mixture model
- closed form
- probability density function
- covariance matrix
- regression model
- low dimensional
- expectation maximization
- mixture model
- model selection
- covariance matrices
- density estimation
- similarity search
- dimensionality reduction
- data points
- high dimensional data
- nearest neighbor
- latent variables
- information retrieval
- supervised learning
- upper bound
- active learning
- pairwise
- feature space