Prediction of magnetization dynamics in a reduced dimensional feature space setting utilizing a low-rank kernel method.
Lukas ExlNorbert J. MauserSebastian SchafferThomas SchreflDieter SuessPublished in: J. Comput. Phys. (2021)
Keyphrases
- kernel methods
- low rank
- feature space
- kernel matrix
- kernel function
- missing data
- matrix factorization
- high dimensional feature space
- low rank matrix
- learning problems
- matrix completion
- high dimensional data
- kernel pca
- singular value decomposition
- machine learning
- linear combination
- convex optimization
- rank minimization
- semi supervised
- semidefinite programming
- reproducing kernel hilbert space
- support vector
- dimensionality reduction
- feature vectors
- learning tasks
- support vector machine
- high dimensional
- high order
- feature selection
- training samples
- input space
- positive semidefinite
- neural network
- feature extraction
- trace norm
- classification accuracy
- multiple kernel learning
- data points
- kernel principal component analysis
- pairwise
- dimension reduction
- collaborative filtering
- data mining
- principal component analysis
- low dimensional
- input data