Quantitative convergence analysis of kernel based large-margin unified machines

DOI10.3934/cpaa.2020180zbMath1445.68190OpenAlexW3027275906MaRDI QIDQ2191836

Jun Fan, Dao-Hong Xiang

Publication date: 26 June 2020

Published in: Communications on Pure and Applied Analysis (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.3934/cpaa.2020180

zbMATH Keywords

convergence ratesregularizationkernel methodsprojection operatorLUMs

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) General nonlinear regression (62J02) 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)

Related Items (1)

Error analysis of classification learning algorithms based on LUMs loss

Uses Software

• AdaBoost.MH
• ElemStatLearn

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Distance-Weighted Discrimination
• Approximation analysis of learning algorithms for support vector regression and quantile regression
• Logistic classification with varying gaussians
• Classification with Gaussians and convex loss. II: Improving error bounds by noise conditions
• Estimating conditional quantiles with the help of the pinball loss
• Multi-kernel regularized classifiers
• Fast rates for support vector machines using Gaussian kernels
• A decision-theoretic generalization of on-line learning and an application to boosting
• Additive logistic regression: a statistical view of boosting. (With discussion and a rejoinder by the authors)
• The covering number in learning theory
• Statistical behavior and consistency of classification methods based on convex risk minimization.
• Optimal aggregation of classifiers in statistical learning.
• Support-vector networks
• Conditional quantiles with varying Gaussians
• Learning rates of least-square regularized regression
• Learning theory estimates via integral operators and their approximations
• 10.1162/153244302760185252
• Capacity of reproducing kernel spaces in learning theory
• ONLINE LEARNING WITH MARKOV SAMPLING
• The sample complexity of pattern classification with neural networks: the size of the weights is more important than the size of the network
• Generalization performance of regularization networks and support vector machines via entropy numbers of compact operators
• Another Look at Distance-Weighted Discrimination
• SVM Soft Margin Classifiers: Linear Programming versus Quadratic Programming
• Data-Dependent Generalization Bounds for Multi-Class Classification
• Hard or Soft Classification? Large-Margin Unified Machines
• Learning rates for regularized least squares ranking algorithm
• Online minimum error entropy algorithm with unbounded sampling
• Convexity, Classification, and Risk Bounds
• Theory of Reproducing Kernels
• The elements of statistical learning. Data mining, inference, and prediction

This page was built for publication: Quantitative convergence analysis of kernel based large-margin unified machines