Optimal learning with Gaussians and correntropy loss

DOI10.1142/S0219530519410124zbMath1462.68159OpenAlexW2989253080MaRDI QIDQ5856264

Fusheng Lv, Jun Fan

Publication date: 25 March 2021

Published in: Analysis and Applications (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1142/s0219530519410124

zbMATH Keywords

convergence ratereproducing kernel Hilbert spaceminimax optimalityGaussian kernelscorrentropy loss

Mathematics Subject Classification ID

General nonlinear regression (62J02) Minimax problems in mathematical programming (90C47) Learning and adaptive systems in artificial intelligence (68T05) Hilbert spaces with reproducing kernels (= (proper) functional Hilbert spaces, including de Branges-Rovnyak and other structured spaces) (46E22) Approximation by arbitrary nonlinear expressions; widths and entropy (41A46)

Related Items (14)

Online gradient descent algorithms for functional data learning ⋮ Learning theory of minimum error entropy under weak moment conditions ⋮ A Statistical Learning Approach to Modal Regression ⋮ Fast rates of minimum error entropy with heavy-tailed noise ⋮ Error analysis on regularized regression based on the maximum correntropy criterion ⋮ Asymptotic properties of Kantorovich-type Szász-Mirakjan operators of higher order ⋮ Convergence theorems in Orlicz and Bögel continuous functions spaces by means of Kantorovich discrete type sampling operators ⋮ Some new inequalities and numerical results of bivariate Bernstein-type operator including Bézier basis and its GBS operator ⋮ On approximation of unbounded functions by certain modified Bernstein operators ⋮ Linear combinations of two Bernstein polynomials ⋮ On wavelet type generalized Bézier operators ⋮ Robust kernel-based distribution regression ⋮ New Insights Into Learning With Correntropy-Based Regression ⋮ Comparison theorems on large-margin learning

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Consistency analysis of an empirical minimum error entropy algorithm
• Quantile regression with \(\ell_1\)-regularization and Gaussian kernels
• Optimal learning rates for least squares regularized regression with unbounded sampling
• Learning rates for kernel-based expectile regression
• Adaptive Bayesian estimation using a Gaussian random field with inverse gamma bandwidth
• Regularization in kernel learning
• Fast rates for support vector machines using Gaussian kernels
• Blind source separation using Renyi's \(\alpha\)-marginal entropies.
• Optimal regression rates for SVMs using Gaussian kernels
• Learning with correntropy-induced losses for regression with mixture of symmetric stable noise
• Correntropy as a novel measure for nonlinearity tests
• Optimal rates for the regularized least-squares algorithm
• An RKHS approach to estimate individualized treatment rules based on functional predictors
• Learning rates for the risk of kernel-based quantile regression estimators in additive models
• The MEE Principle in Data Classification: A Perceptron-Based Analysis
• Learning Theory
• Support Vector Machines
• Correntropy: Properties and Applications in Non-Gaussian Signal Processing
• Gradient descent for robust kernel-based regression
• Generalized correlation function: definition, properties, and application to blind equalization
• A Statistical Learning Approach to Modal Regression
• Information Theoretic Learning
• A Regularized Correntropy Framework for Robust Pattern Recognition
• Distributed learning with indefinite kernels
• Regularization schemes for minimum error entropy principle
• Learning rates for regularized least squares ranking algorithm
• Robust Principal Component Analysis Based on Maximum Correntropy Criterion
• Learning Rates for Classification with Gaussian Kernels

This page was built for publication: Optimal learning with Gaussians and correntropy loss