On the Fine-Grained Complexity of Empirical Risk Minimization: Kernel Methods and Neural Networks.
Arturs BackursPiotr IndykLudwig SchmidtPublished in: CoRR (2017)
Keyphrases
- fine grained
- kernel methods
- empirical risk minimization
- neural network
- uniform convergence
- reproducing kernel hilbert space
- learning problems
- kernel function
- statistical learning theory
- support vector
- access control
- machine learning
- kernel matrix
- support vector machine
- learning tasks
- feature space
- vc dimension
- multiple kernel learning
- worst case
- gaussian kernel
- svm classifier
- special case
- high dimensional feature space
- decision trees
- learning algorithm
- markov random field
- empirical risk