Regression of a data matrix on descriptors of both its rows and of its columns via latent variables: L-PLSR.
Harald MartensEndre AnderssenArnar FlatbergLars Halvor GidskehaugMartin HøyFrank WestadAnette ThyboMagni MartensPublished in: Comput. Stat. Data Anal. (2005)
Keyphrases
- latent variables
- data matrix
- rows and columns
- missing values
- matrix factorization
- original data
- low rank
- gene expression data
- singular value decomposition
- probabilistic model
- nonnegative matrix factorization
- barcode
- random variables
- prior knowledge
- model selection
- topic models
- missing data
- singular values
- feature vectors
- data sets
- least squares
- semi supervised
- small number
- collaborative filtering
- linear combination
- gene expression
- information extraction
- image reconstruction
- support vector
- machine learning