Learning rates for l^1-regularized kernel classifiers
Summary: We consider a family of classification algorithms generated from a regularization kernel scheme associated with \(l^1\)-regularizer and convex loss function. Our main purpose is to provide an explicit convergence rate for the excess misclassification error of the produced classifiers. The error decomposition includes approximation error, hypothesis error, and sample error. We apply some novel techniques to estimate the hypothesis error and sample error. Learning rates are eventually derived under some assumptions on the kernel, the input space, the marginal distribution, and the approximation error.
- Classification with polynomial kernels and l^1-coefficient regularization
- Learning rates for regularized classifiers using multivariate polynomial kernels
- Multi-kernel regularized classifiers
- An approximation theory approach to learning with \(\ell^1\) regularization
- Approximation with polynomial kernels and SVM classifiers
- Optimal learning rates for kernel partial least squares
- An approximation theory approach to learning with \(\ell^1\) regularization
- Learning rates of kernel-based robust classification
- Regularized ranking with convex losses and \(\ell^1\)-penalty
- Approximate minimization of the regularized expected error over kernel models
- The learning rate of \(l_2\)-coefficient regularized classification with strong loss
- scientific article; zbMATH DE number 7295804 (Why is no real title available?)
- Classification with polynomial kernels and l^1-coefficient regularization
- Learning Rates of lq Coefficient Regularization Learning with Gaussian Kernel
- Learning rates for multi-kernel linear programming classifiers
- Learning by nonsymmetric kernels with data dependent spaces and \(\ell^1\)-regularizer
- Concentration estimates for learning with \(\ell ^{1}\)-regularizer and data dependent hypothesis spaces
- Learning sparse low-threshold linear classifiers
- Error analysis of classification learning algorithms based on LUMs loss
- ℓ 1 -regularization learning based on Huber regression
- Multi-kernel regularized classifiers
- Ideal regularization for learning kernels from labels
- Learning rates for regularized classifiers using multivariate polynomial kernels
This page was built for publication: Learning rates for \(l^1\)-regularized kernel classifiers
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1789959)
