Learning rates for the kernel regularized regression with a differentiable strongly convex loss (Q2191832): Difference between revisions

From MaRDI portal

Jump to:navigation, search

Latest revision as of 10:21, 17 December 2024

scientific article

Language	Label	Description	Also known as
English	Learning rates for the kernel regularized regression with a differentiable strongly convex loss	scientific article

Statements

scholarly article

0 references

Learning rates for the kernel regularized regression with a differentiable strongly convex loss (English)

0 references

0 references

0 references

0 references

Communications on Pure and Applied Analysis

0 references

publication date

26 June 2020

0 references

zbMATH Keywords

kernel-regularized regression

0 references

learning rate

0 references

differentiable strongly convex loss

0 references

conjugate loss

0 references

\(K\)-functional

0 references

maximum mean discrepancy (MMD)

0 references

Hutchinson metric

0 references

reproducing-kernel Hilbert space

0 references

describes a project that uses

0 references

0 references

MaRDI profile type

0 references

full work available at URL

https://doi.org/10.3934/cpaa.2020176

0 references

0 references

Theory of Reproducing Kernels

0 references

0 references

Convexity, Classification, and Risk Bounds

0 references

On regularization algorithms in learning theory

0 references

Convex analysis and monotone operator theory in Hilbert spaces

0 references

0 references

Convergence rates of Kernel Conjugate Gradient for random design regression

0 references

Optimal rates for regularization of statistical inverse learning problems

0 references

A representer theorem for deep kernel learning

0 references

0 references

epsilon-entropy of convex sets and functions

0 references

Optimal rates for the regularized least-squares algorithm

0 references

GENERALIZATION BOUNDS OF REGULARIZATION ALGORITHMS DERIVED SIMULTANEOUSLY THROUGH HYPOTHESIS SPACE COMPLEXITY, ALGORITHMIC STABILITY AND DATA QUALITY

0 references

0 references

0 references

Editorial: On the interface of statistics and machine learning

0 references

0 references

Consistency and robustness of kernel-based regression in convex risk minimization

0 references

Consistency of kernel-based quantile regression

0 references

Learning rates for the risk of kernel-based quantile regression estimators in additive models

0 references

On the robustness of regularized pairwise learning methods based on kernels

0 references

On the mathematical foundations of learning

0 references

Best choices for regularization parameters in learning theory: on the bias-variance problem.

0 references

Robustness of reweighted least squares kernel based regression

0 references

Model selection for regularized least-squares algorithm in learning theory

0 references

0 references

Learning sets with separating kernels

0 references

Optimal regression rates for SVMs using Gaussian kernels

0 references

Regularization networks and support vector machines

0 references

Learning rates for kernel-based expectile regression

0 references

Covering Numbers for Convex Functions

0 references

Gradient descent for robust kernel-based regression

0 references

On qualitative robustness of support vector machines

0 references

The elements of statistical learning. Data mining, inference, and prediction

0 references

0 references

Optimal rates for spectral algorithms with least-squares regression over Hilbert spaces

0 references

Application of integral operator for vector-valued regression learning

0 references

A review on consistency and robustness properties of support vector machines for heavy-tailed distributions

0 references

0 references

0 references

Kernel Mean Embedding of Distributions: A Review and Beyond

0 references

0 references

Convex Optimization in Normed Spaces

0 references

0 references

0 references

On approximation by reproducing kernel spaces in weighted \(L^p\) spaces

0 references

On approximation by spherical zonal translation networks based on Bochner-Riesz means

0 references

On the K-functional in learning theory

0 references

Error analysis on Hérmite learning with gradient data

0 references

A way of construction spherical zonal translation network operators with linear bounded operators

0 references

The convergence rate for a \(K\)-functional in learning theory

0 references

The learning rate of \(l_2\)-coefficient regularized classification with strong loss

0 references

Learning rates for least square regressions with coefficient regularization

0 references

ESTIMATING THE APPROXIMATION ERROR IN LEARNING THEORY

0 references

Learning theory estimates via integral operators and their approximations

0 references

The convergence rate of semi-supervised regression with quadratic loss

0 references

Hilbert space embeddings and metrics on probability measures

0 references

10.1162/1532443041827925

0 references

Estimating conditional quantiles with the help of the pinball loss

0 references

Support Vector Machines

0 references

Application of integral operator for regularized least-square regression

0 references

Analysis of support vector machines regression

0 references

Fast learning rates for regularized regression algorithms

0 references

0 references

CONVERGENCE ANALYSIS OF COEFFICIENT-BASED REGULARIZATION UNDER MOMENT INCREMENTAL CONDITION

0 references

Convergence rate of SVM for kernel-based robust regression

0 references

ERM learning with unbounded sampling

0 references

Optimal learning rates for least squares regularized regression with unbounded sampling

0 references

Learning rates of least-square regularized regression

0 references

Conditional quantiles with varying Gaussians

0 references

ERM scheme for quantile regression

0 references

Statistical behavior and consistency of classification methods based on convex risk minimization.

0 references

Capacity of reproducing kernel spaces in learning theory

0 references

Deep distributed convolutional neural networks: Universality

0 references

Universality of deep convolutional neural networks

0 references

Approximation with polynomial kernels and SVM classifiers

0 references

Identifiers

zbMATH Open document ID

0 references

Mathematics Subject Classification ID

0 references

0 references

0 references

0 references

zbMATH DE Number

0 references

0 references

10.3934/CPAA.2020176

0 references

Sitelinks

Mathematics(1 entry)

mardi Publication:2191832

Retrieved from "https://portal.mardi4nfdi.de/w/index.php?title=Item:Q2191832&oldid=38933375"