Training very large scale nonlinear SVMs using Alternating Direction Method of Multipliers coupled with the Hierarchically Semi-Separable kernel approximations.
Stefano CipollaJacek GondzioPublished in: CoRR (2021)
Keyphrases
- support vector
- linear svm
- kernel function
- kernel principal component analysis
- training set
- kernel pca
- high dimensional feature space
- kernel svms
- alternating direction method of multipliers
- kernel methods
- feature space
- text categorization
- training examples
- multi class
- feature selection
- multiple kernel learning
- face recognition
- convex optimization
- machine learning
- stochastic gradient descent
- high dimensional
- maximum margin
- svm classifier
- support vector machine
- markov random field
- principal component analysis