On the Fine-Grained Complexity of Empirical Risk Minimization: Kernel Methods and Neural Networks.
Arturs BackursPiotr IndykLudwig SchmidtPublished in: NIPS (2017)
Keyphrases
- fine grained
- kernel methods
- empirical risk minimization
- neural network
- uniform convergence
- reproducing kernel hilbert space
- learning problems
- support vector
- kernel function
- statistical learning theory
- machine learning
- access control
- feature space
- kernel matrix
- support vector machine
- kernel machines
- generalization bounds
- worst case
- multiple kernel learning
- empirical risk
- learning tasks
- real valued
- high dimensional feature space
- gaussian kernel
- vc dimension
- data mining