Learning theory of minimum error entropy under weak moment conditions

DOI10.1142/S0219530521500044zbMATH Open1482.68200OpenAlexW3127795058MaRDI QIDQ5037873FDOQ5037873

Authors: Shouyou Huang, Yun-Long Feng, Qiang Wu 

Publication date: 4 March 2022

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

Full work available at URL: https://doi.org/10.1142/s0219530521500044

Recommendations

• Fast rates of minimum error entropy with heavy-tailed noise
• Learning theory approach to minimum error entropy criterion
• Some further results on the minimum error entropy estimation
• Online minimum error entropy algorithm with unbounded sampling
• Distributed minimum error entropy algorithms

zbMATH Keywords

entropycalibrationrobust learningmoment conditionBernstein conditionempirical U-statistics minimization

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Computational learning theory (68Q32)

Cites Work

• Learning Theory
• Support Vector Machines
• Title not available (Why is that?)
• Probability Inequalities for Sums of Bounded Random Variables
• Robust Statistics
• Statistical behavior and consistency of classification methods based on convex risk minimization.
• Approximation theorems of mathematical statistics
• Information theoretic learning. Renyi's entropy and kernel perspectives
• Convexity, Classification, and Risk Bounds
• Blind source separation using Renyi's \(\alpha\)-marginal entropies.
• Consistency analysis of an empirical minimum error entropy algorithm
• The MEE principle in data classification: a perceptron-based analysis
• Learning theory approach to minimum error entropy criterion
• Regularization schemes for minimum error entropy principle
• Empirical minimization
• The convergence rate of a regularized ranking algorithm
• Online regularized pairwise learning with least squares loss
• A Statistical Learning Approach to Modal Regression
• Learning rates for regularized least squares ranking algorithm
• Learning under \((1 + \epsilon)\)-moment conditions
• Fast rates in statistical and online learning
• Distributed kernel gradient descent algorithm for minimum error entropy principle
• A statistical learning assessment of Huber regression
• Optimal learning with Gaussians and correntropy loss
• Convergence of Gradient Descent for Minimum Error Entropy Principle in Linear Regression
• Minimum Total Error Entropy Method for Parameter Estimation
• Kernel gradient descent algorithm for information theoretic learning
• New insights into learning with correntropy-based regression
• Distributed minimum error entropy algorithms

Cited In (23)

• Linear combinations of two Bernstein polynomials
• On the convergence of gradient descent for robust functional linear regression
• Rates of approximation by ReLU shallow neural networks
• Online minimum error entropy algorithm with unbounded sampling
• On choosing initial values of iteratively reweighted \(\ell_1\) algorithms for the piece-wise exponential penalty
• On approximation of unbounded functions by certain modified Bernstein operators
• Some further results on the minimum error entropy estimation
• Compressed data separation via unconstrained l1-split analysis
• Distributed minimum error entropy algorithms
• Convergence theorems in Orlicz and Bögel continuous functions spaces by means of Kantorovich discrete type sampling operators
• Approximation by modified Bernstein polynomials based on real parameters
• Learning theory approach to minimum error entropy criterion
• On weak learning
• Some new fractional integral inequalities for \((h_1, h_2)\)-convex functions
• Optimality of robust online learning
• On wavelet type generalized Bézier operators
• Approximation properties of exponential type operators connected to \(p(x)=2x^{3/2}\)
• Error analysis of classification learning algorithms based on LUMs loss
• Some new inequalities and numerical results of bivariate Bernstein-type operator including Bézier basis and its GBS operator
• Shape preserving properties of \((\mathfrak{p},\mathfrak{q})\) Bernstein Bèzier curves and corresponding results over \([a,b]\)
• Asymptotic properties of Kantorovich-type Szász-Mirakjan operators of higher order
• A metric entropy bound is not sufficient for learnability
• Minimum error entropy classification.

This page was built for publication: Learning theory of minimum error entropy under weak moment conditions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5037873)