Comparison theorems on large-margin learning

DOI10.1142/S0219691321500156OpenAlexW3155738301MaRDI QIDQ5022946

Jun Fan, Amina Benabid, Dao-Hong Xiang

Publication date: 20 January 2022

Published in: International Journal of Wavelets, Multiresolution and Information Processing (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1908.04470

zbMATH Keywords

comparison theoremmisclassification errorgeneralization errorGaussian kernelslarge-margin unified machine

Mathematics Subject Classification ID

Computational learning theory (68Q32) Analysis of algorithms (68W40) Approximation by arbitrary nonlinear expressions; widths and entropy (41A46)

Related Items (1)

Error analysis of classification learning algorithms based on LUMs loss

Uses Software

• ElemStatLearn

Cites Work

• Unnamed Item
• Unnamed Item
• Distance-Weighted Discrimination
• Logistic classification with varying gaussians
• Classification with Gaussians and convex loss. II: Improving error bounds by noise conditions
• Learning with varying insensitive loss
• A new comparison theorem on conditional quantiles
• Adaptive Bayesian estimation using a Gaussian random field with inverse gamma bandwidth
• Fast rates for support vector machines using Gaussian kernels
• Statistical behavior and consistency of classification methods based on convex risk minimization.
• Optimal aggregation of classifiers in statistical learning.
• Support-vector networks
• Optimal rates for the regularized least-squares algorithm
• Another Look at Distance-Weighted Discrimination
• SVM Soft Margin Classifiers: Linear Programming versus Quadratic Programming
• A Statistical Learning Approach to Modal Regression
• Convergence analysis of distributed multi-penalty regularized pairwise learning
• Hard or Soft Classification? Large-Margin Unified Machines
• Learning rates for regularized least squares ranking algorithm
• Convexity, Classification, and Risk Bounds
• Optimal learning with Gaussians and correntropy loss
• The elements of statistical learning. Data mining, inference, and prediction
• On the convergence rate and some applications of regularized ranking algorithms

This page was built for publication: Comparison theorems on large-margin learning