Efficient learning of supervised kernels with a graph-based loss function.
Binbin PanWen-Sheng ChenBo ChenChen XuPublished in: Inf. Sci. (2016)
Keyphrases
- loss function
- efficient learning
- reproducing kernel hilbert space
- semi supervised
- support vector
- pairwise
- learning algorithm
- convex loss functions
- logistic regression
- norm regularization
- empirical risk
- learning to rank
- kernel function
- kernel learning
- feature selection
- risk minimization
- kernel methods
- semi supervised learning
- supervised learning
- boosting framework
- pattern languages
- structured prediction
- machine learning
- gaussian kernels
- feature space
- unlabeled data
- stochastic gradient descent
- solution path
- multiple kernel learning
- binary classification
- active learning