Generalization properties of hyper-RKHS and its applications

MaRDI QIDQ5159408zbMATH OpenFDO

Authors

Publication date 27 October 2021

Full work available at URL https://arxiv.org/abs/1809.09910, https://jmlr.csail.mit.edu/papers/v22/19-482.html

zbMATH Keywords

approximation theoryhyper-RKHSkernel learningout-of-sample extensions

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• scientific article; zbMATH DE number 5957287
• Regularization in kernel learning
• Learning general Gaussian kernel hyperparameters for SVR
• On convergence of kernel learning estimators
• Analysis of regularized least-squares in reproducing kernel Kreĭn spaces

Cites work

• A Bayesian multiple kernel learning framework for single and multiple output regression
• A universal sampling method for reconstructing signals with simple Fourier transforms
• Algorithms for learning kernels based on centered alignment
• Approximation analysis of learning algorithms for support vector regression and quantile regression
• Breaking the curse of dimensionality with convex neural networks
• Concentration estimates for learning with unbounded sampling
• Deep metric learning using triplet network
• Distributed learning with regularized least squares
• Divide and conquer kernel ridge regression: a distributed algorithm with minimax optimal rates
• Efficient regularized least-squares algorithms for conditional ranking on relational data
• Estimating conditional quantiles with the help of the pinball loss
• Fast learning rate of multiple kernel learning: trade-off between sparsity and smoothness
• Harder, Better, Faster, Stronger Convergence Rates for Least-Squares Regression
• scientific article; zbMATH DE number 5957287 (Why is no real title available?)
• scientific article; zbMATH DE number 3449274 (Why is no real title available?)
• scientific article; zbMATH DE number 1843268 (Why is no real title available?)
• scientific article; zbMATH DE number 7306853 (Why is no real title available?)
• Indefinite proximity learning: a review
• Large-scale linear support vector regression
• Learning data-adaptive non-parametric kernels
• Learning rates of least-square regularized regression
• Learning Theory
• Learning Theory and Kernel Machines
• Learning theory of distributed regression with bias corrected regularization kernel network
• Learning with varying insensitive loss
• Linearized two-layers neural networks in high dimension
• Multiple kernel learning algorithms
• Optimal learning rates for least squares regularized regression with unbounded sampling
• Optimal rates for the regularized least-squares algorithm
• Pairwise independence and derandomization.
• Quantile regression with _1-regularization and Gaussian kernels
• Regularization in kernel learning
• Sparse kernel regression with coefficient-based \(\ell_q\)-regularization
• Support vector machine soft margin classifiers: error analysis
• Support Vector Machines
• Theory of Reproducing Kernels
• Theory of reproducing kernels and applications
• Wide neural networks of any depth evolve as linear models under gradient descent ^*

Cited in

(3)

• Generalization properties of doubly stochastic learning algorithms
• Which spaces can be embedded in reproducing kernel Hilbert spaces?
• Polynomial-based kernel reproduced gradient descent for stochastic optimization

This page was built for publication: Generalization properties of hyper-RKHS and its applications

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5159408)