Gradient descent for robust kernel-based regression
From MaRDI portal
(Redirected from Publication:4571003)
Recommendations
- Consistency and robustness of kernel-based regression in convex risk minimization
- Convergence rate of SVM for kernel-based robust regression
- Kernel-based maximum correntropy criterion with gradient descent method
- An RKHS approach to robust functional linear regression
- Learning gradients by a gradient descent algorithm
Cites work
- 10.1162/15324430152748236
- A General Qualitative Definition of Robustness
- Adaptive kernel methods using the balancing principle
- Breakdown points of Cauchy regression-scale estimators
- Concentration estimates for learning with \(\ell ^{1}\)-regularizer and data dependent hypothesis spaces
- Correntropy: Properties and Applications in Non-Gaussian Signal Processing
- Early stopping and non-parametric regression: an optimal data-dependent stopping rule
- ESTIMATING THE APPROXIMATION ERROR IN LEARNING THEORY
- Generalized correlation function: definition, properties, and application to blind equalization
- scientific article; zbMATH DE number 3320125 (Why is no real title available?)
- Information theoretic learning. Renyi's entropy and kernel perspectives
- Iterative regularization for learning with convex loss functions
- Learning Theory
- Learning theory estimates via integral operators and their approximations
- Learning theory of distributed spectral algorithms
- Learning with coefficient-based regularization and ^1-penalty
- Learning with the maximum correntropy criterion induced losses for regression
- Multivariate adaptive regression splines
- On early stopping in gradient descent learning
- On regularization algorithms in learning theory
- Optimal rates for the regularized least-squares algorithm
- Robust Estimation of a Location Parameter
- Robust Statistics
- Robust Statistics
- Robustness of reweighted least squares kernel based regression
- Some results on Tchebycheffian spline functions and stochastic processes
- Support Vector Machines
- Theory and Methods Related to the Singular-Function Expansion and Landweber’s Iteration for Integral Equations of the First Kind
- Theory of Reproducing Kernels
- Thresholded spectral algorithms for sparse approximations
Cited in
(13)- Learning rates for the kernel regularized regression with a differentiable strongly convex loss
- Kernel-based maximum correntropy criterion with gradient descent method
- New insights into learning with correntropy-based regression
- Robust kernel-based distribution regression
- Optimal learning with Gaussians and correntropy loss
- On the convergence of gradient descent for robust functional linear regression
- Distributed robust regression with correntropy losses and regularization kernel networks
- Optimality of robust online learning
- Least squares regression under weak moment conditions
- Robust kernel-based gradient descent with random features
- Online outcome weighted learning with general loss functions
- Tikhonov regularization for Gaussian empirical gain maximization in RKHS is consistent
- Robust online learning algorithms for functional linear regression
This page was built for publication: Gradient descent for robust kernel-based regression
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4571003)
