Refined generalization bounds of gradient learning over reproducing kernel Hilbert spaces
From MaRDI portal
Recommendations
- Rademacher Chaos Complexities for Learning the Kernel Problem
- Gradient learning in a classification setting by gradient descent
- Learning gradients by a gradient descent algorithm
- Learning with generalization capability by kernel methods of bounded complexity
- Refined Rademacher chaos complexity bounds with applications to the multikernel learning problem
Cites work
- U-Processes and Preference Learning
- A new concentration result for regularized risk minimizers
- An Adaptive Estimation of Dimension Reduction Space
- An empirical feature-based learning algorithm producing sparse approximations
- Better Subset Regression Using the Nonnegative Garrote
- Component selection and smoothing in multivariate nonparametric regression
- Estimation of gradients and coordinate covariation in classification
- Geometry on probability spaces
- Hessian eigenmaps: Locally linear embedding techniques for high-dimensional data
- High-dimensional additive modeling
- scientific article; zbMATH DE number 2089352 (Why is no real title available?)
- Learning coordinate covariances via gradients
- Learning gradients on manifolds
- Learning gradients via an early stopping gradient descent method
- Learning gradients: predictive models that infer geometry and statistical dependence
- Learning sparse gradients for variable selection and dimension reduction
- Learning theory approach to minimum error entropy criterion
- Least angle regression. (With discussion)
- Limit theorems for \(U\)-processes
- Local Rademacher complexities
- Model-Free Variable Selection
- On ranking and generalization bounds
- On the mathematical foundations of learning
- Ranking and empirical minimization of \(U\)-statistics
- Refined Rademacher chaos complexity bounds with applications to the multikernel learning problem
- Sparse additive models
- Support Vector Machines
- Variable Selection via Nonconcave Penalized Likelihood and its Oracle Properties
- Weak convergence and empirical processes. With applications to statistics
Cited in
(4)- Refined Rademacher chaos complexity bounds with applications to the multikernel learning problem
- Kernelized elastic net regularization: generalization bounds, and sparse recovery
- Learning with generalization capability by kernel methods of bounded complexity
- Derivative reproducing properties for kernel methods in learning theory
This page was built for publication: Refined generalization bounds of gradient learning over reproducing kernel Hilbert spaces
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5380250)
