Convergence acceleration of alternating least squares with a matrix polynomial predictive model for PARAFAC decomposition of a tensor.
Ming ShiJianQiu ZhangBo HuBin WangQiyong LuPublished in: EUSIPCO (2017)
Keyphrases
- predictive model
- tensor decomposition
- alternating least squares
- tensor factorization
- negative matrix factorization
- nonnegative matrix factorization
- data representation
- low rank approximation
- low rank
- historical data
- matrix factorization
- singular vectors
- iterative algorithms
- artificial neural networks
- high order
- decision trees
- neural network
- sparse representation
- prediction model
- singular value decomposition
- classification rules
- document clustering
- convergence rate
- classification models
- principal component analysis
- stochastic gradient descent
- probabilistic model
- spectral clustering
- missing data
- kernel matrix
- linear combination
- dimensionality reduction
- higher order
- data analysis
- learning algorithm
- genetic algorithm