Error analysis of classification learning algorithms based on LUMs loss

DOI10.3934/MFC.2022028MaRDI QIDQ6112861zbMATH OpenOpenAlexFDO

Authors

Publication date 7 August 2023

Published in Mathematical Foundations of Computing (Search for Journal in Brave)

Full work available at URL https://doi.org/10.3934/mfc.2022028

zbMATH Keywords

classificationerror boundlearning ratelearning theoryLUMs loss

Mathematics Subject Classification ID

Hilbert spaces with reproducing kernels (= (proper) functional Hilbert spaces, including de Branges-Rovnyak and other structured spaces) (46E22) Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Comparison theorems on large-margin learning
• Quantitative convergence analysis of kernel based large-margin unified machines
• Error analysis on regularized learning
• Learning rates for l^1-regularized kernel classifiers
• Support vector machine soft margin classifiers: error analysis

Cites work

• Another look at distance-weighted discrimination
• Approximation analysis of learning algorithms for support vector regression and quantile regression
• Comparison theorems on large-margin learning
• Consistency of Support Vector Machines and Other Regularized Kernel Classifiers
• Convexity, Classification, and Risk Bounds
• Distance-Weighted Discrimination
• Estimating conditional quantiles with the help of the pinball loss
• Hard or soft classification? Large-margin unified machines
• scientific article; zbMATH DE number 7415114 (Why is no real title available?)
• Learning rates of least-square regularized regression
• Learning theory estimates via integral operators and their approximations
• Learning theory of minimum error entropy under weak moment conditions
• Optimal aggregation of classifiers in statistical learning.
• Quantitative convergence analysis of kernel based large-margin unified machines
• Statistical behavior and consistency of classification methods based on convex risk minimization.
• The influence of observations on misclassification probability estimates in linear discriminant analysis
• Theory of Reproducing Kernels

Cited in

(7)

• Comparison theorems on large-margin learning
• Relevant sampling in a reproducing kernel subspace of Orlicz space
• On choosing initial values of iteratively reweighted \(\ell_1\) algorithms for the piece-wise exponential penalty
• Large margin unified machines with non-i.i.d. process
• Elevating large language model reasoning ability with auto-enhanced zero-shot prompts
• Kernel support matrix machines with ramp loss
• Regularized kernel networks with convex p-Lipschitz loss

This page was built for publication: Error analysis of classification learning algorithms based on LUMs loss

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6112861)